US:CPS: EmploymentStatus classification:: us_cps_2016
bdanalytics
Date: (Fri) Apr 22, 2016
Introduction:
Data: Source: Training: https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/CPSData.csv
New:
Time period:
Synopsis:
Based on analysis utilizing <> techniques,
Summary of key steps & error improvement stats:
Prediction Accuracy Enhancement Options:
- transform.data chunk:
- derive features from multiple features
- manage.missing.data chunk:
- Not fill missing vars
- Fill missing numerics with a different algorithm
- Fill missing chars with data based on clusters
[](.png)
Potential next steps include:
- Organization:
- Categorize by chunk
- Priority criteria:
- Ease of change
- Impacts report
- Cleans innards
- Bug report
- all chunks:
- at chunk-end rm(!glb_)
- manage.missing.data chunk:
- cleaner way to manage re-splitting of training vs. new entity
- extract.features chunk:
- Add n-grams for glbFeatsText
- “RTextTools”, “tau”, “RWeka”, and “textcat” packages
- Add n-grams for glbFeatsText
- fit.models chunk:
- Classification: Plot AUC Curves for all models & highlight glbMdlSel
- Prediction accuracy scatter graph:
- Add tiles (raw vs. PCA)
- Use shiny for drop-down of “important” features
Use plot.ly for interactive plots ?
- Change .fit suffix of model metrics to .mdl if it’s data independent (e.g. AIC, Adj.R.Squared - is it truly data independent ?, etc.)
- create a custom model for rpart that has minbucket as a tuning parameter
varImp for randomForest crashes in caret version:6.0.41 -> submit bug report
- Probability handling for multinomials vs. desired binomial outcome
- ROCR currently supports only evaluation of binary classification tasks (version 1.0.7)
extensions toward multiclass classification are scheduled for the next release
- fit.all.training chunk:
- myplot_prediction_classification: displays ‘x’ instead of ‘+’ when there are no prediction errors
- Compare glb_sel_mdl vs. glb_fin_mdl:
- varImp
- Prediction differences (shd be minimal ?)
- Move glb_analytics_diag_plots to mydsutils.R: (+) Easier to debug (-) Too many glb vars used
- Add print(ggplot.petrinet(glb_analytics_pn) + coord_flip()) at the end of every major chunk
- Parameterize glb_analytics_pn
- Move glb_impute_missing_data to mydsutils.R: (-) Too many glb vars used; glb_<>_df reassigned
- Do non-glm methods handle interaction terms ?
- f-score computation for classifiers should be summation across outcomes (not just the desired one ?)
- Add accuracy computation to glb_dmy_mdl in predict.data.new chunk
- Why does splitting fit.data.training.all chunk into separate chunks add an overhead of ~30 secs ? It’s not rbind b/c other chunks have lower elapsed time. Is it the number of plots ?
- Incorporate code chunks in print_sessionInfo
- Test against
- projects in github.com/bdanalytics
- lectures in jhu-datascience track
Analysis:
rm(list = ls())
set.seed(12345)
options(stringsAsFactors = FALSE)
source("~/Dropbox/datascience/R/mycaret.R")
source("~/Dropbox/datascience/R/mydsutils.R")## Loading required package: caret## Loading required package: lattice## Loading required package: ggplot2source("~/Dropbox/datascience/R/mypetrinet.R")
source("~/Dropbox/datascience/R/myplclust.R")
source("~/Dropbox/datascience/R/myplot.R")
source("~/Dropbox/datascience/R/myscript.R")
source("~/Dropbox/datascience/R/mytm.R")
# Gather all package requirements here
suppressPackageStartupMessages(require(doMC))
glbCores <- 6 # of cores on machine - 2
registerDoMC(glbCores)
suppressPackageStartupMessages(require(caret))
require(plyr)## Loading required package: plyrrequire(dplyr)## Loading required package: dplyr##
## Attaching package: 'dplyr'## The following objects are masked from 'package:plyr':
##
## arrange, count, desc, failwith, id, mutate, rename, summarise,
## summarize## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionrequire(knitr)## Loading required package: knitrrequire(stringr)## Loading required package: stringr#source("dbgcaret.R")
#packageVersion("snow")
#require(sos); findFn("cosine", maxPages=2, sortby="MaxScore")
# Analysis control global variables
# Inputs
# url/name = "<PathPointer>"; if url specifies a zip file, name = "<filename>";
# or named collection of <PathPointer>s
# sep = choose from c(NULL, "\t")
glbObsTrnFile <- list(url = "https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/CPSData.csv"
# or list(url = c(NULL, <.inp1> = "<path1>", <.inp2> = "<path2>"))
, splitSpecs = list(method = "condition" # default when glbObsNewFile is NULL
# select from c("copy", NULL ???, "condition", "sample", )
# ,nRatio = 0.3 # > 0 && < 1 if method == "sample"
# ,seed = 123 # any integer or glbObsTrnPartitionSeed if method == "sample"
,condition = 'is.na(EmploymentStatus)' #; '<var> <condition_operator> <value>'
)
)
glbObsNewFile <- NULL # default OR list(url = "<obsNewFileName>")
glbObsDropCondition <- NULL # : default
# enclose in single-quotes b/c condition might include double qoutes
# use | & ; NOT || &&
# '<condition>'
# 'grepl("^First Draft Video:", glbObsAll$Headline)'
# 'is.na(glbObsAll[, glb_rsp_var_raw])'
# '(is.na(glbObsAll[, glb_rsp_var_raw]) & grepl("Train", glbObsAll[, glbFeatsId]))'
# 'is.na(strptime(glbObsAll[, "Date"], glbFeatsDateTime[["Date"]]["format"], tz = glbFeatsDateTime[["Date"]]["timezone"]))'
#nrow(do.call("subset",list(glbObsAll, parse(text=paste0("!(", glbObsDropCondition, ")")))))
glb_obs_repartition_train_condition <- NULL # : default
# "<condition>"
glb_max_fitobs <- NULL # or any integer
glbObsTrnPartitionSeed <- 123 # or any integer
glb_is_regression <- FALSE; glb_is_classification <- !glb_is_regression;
glb_is_binomial <- FALSE # or TRUE or FALSE
glb_rsp_var_raw <- "EmploymentStatus"
# for classification, the response variable has to be a factor
glb_rsp_var <- "EmploymentStatus.fctr"
# if the response factor is based on numbers/logicals e.g (0/1 OR TRUE/FALSE vs. "A"/"B"),
# or contains spaces (e.g. "Not in Labor Force")
# caret predict(..., type="prob") crashes
glb_map_rsp_raw_to_var <- #NULL
function(raw) {
# return(raw ^ 0.5)
# return(log(raw))
# return(log(1 + raw))
# return(log10(raw))
# return(exp(-raw / 2))
# ret_vals <- rep_len(NA, length(raw)); ret_vals[!is.na(raw)] <- ifelse(raw[!is.na(raw)] == 1, "Y", "N"); return(relevel(as.factor(ret_vals), ref="N"))
# as.factor(paste0("B", raw))
as.factor(gsub(" ", "\\.", raw))
}
#if glb_rsp_var_raw is numeric:
#print(summary(glbObsAll[, glb_rsp_var_raw]))
#glb_map_rsp_raw_to_var(tst <- c(NA, as.numeric(summary(glbObsAll[, glb_rsp_var_raw]))))
#if glb_rsp_var_raw is character:
#print(table(glbObsAll[, glb_rsp_var_raw], useNA = "ifany"))
#print(table(glb_map_rsp_raw_to_var(tst <- glbObsAll[, glb_rsp_var_raw]), useNA = "ifany"))
glb_map_rsp_var_to_raw <- #NULL
function(var) {
# return(var ^ 2.0)
# return(exp(var))
# return(10 ^ var)
# return(-log(var) * 2)
# as.numeric(var)
# levels(var)[as.numeric(var)]
gsub("\\.", " ", levels(var)[as.numeric(var)])
# c("<=50K", " >50K")[as.numeric(var)]
# c(FALSE, TRUE)[as.numeric(var)]
}
#print(table(glb_map_rsp_var_to_raw(glb_map_rsp_raw_to_var(tst)), useNA = "ifany"))
if ((glb_rsp_var != glb_rsp_var_raw) && is.null(glb_map_rsp_raw_to_var))
stop("glb_map_rsp_raw_to_var function expected")
# List info gathered for various columns
# <col_name>: <description>; <notes>
# PeopleInHousehold: The number of people in the interviewee's household.
# Region: The census region where the interviewee lives.
# State: The state where the interviewee lives.
# MetroAreaCode: A code that identifies the metropolitan area in which the interviewee lives (missing if the interviewee does not live in a metropolitan area). The mapping from codes to names of metropolitan areas is provided in the file MetroAreaCodes.csv.
# Age: The age, in years, of the interviewee. 80 represents people aged 80-84, and 85 represents people aged 85 and higher.
# Married: The marriage status of the interviewee.
# Sex: The sex of the interviewee.
# Education: The maximum level of education obtained by the interviewee.
# Race: The race of the interviewee.
# Hispanic: Whether the interviewee is of Hispanic ethnicity.
# CountryOfBirthCode: A code identifying the country of birth of the interviewee. The mapping from codes to names of countries is provided in the file CountryCodes.csv.
# Citizenship: The United States citizenship status of the interviewee.
# EmploymentStatus: The status of employment of the interviewee.
# Industry: The industry of employment of the interviewee (only available if they are employed).
# currently does not handle more than 1 column; consider concatenating multiple columns
# If glbFeatsId == NULL, ".rownames <- as.numeric(row.names())" is the default
glbFeatsId <- NULL # choose from c(NULL : default, "<id_feat>")
glbFeatsCategory <- NULL # choose from c(NULL : default, "<category_feat>")
# User-specified exclusions
glbFeatsExclude <- c(NULL
# Feats that shd be excluded due to known causation by prediction variable
# , "<feat1", "<feat2>"
# Feats that are factors with unique values (as % of nObs) > 49 (empirically derived)
# Feats that are linear combinations (alias in glm)
# Feature-engineering phase -> start by excluding all features except id & category & work each one in
,"Education","Married","MetroArea"
,"Industry"
,"MetroArea.fctr","State.fctr","Country.fctr"
,".pos",".pos.y",".rownames"
)
if (glb_rsp_var_raw != glb_rsp_var)
glbFeatsExclude <- union(glbFeatsExclude, glb_rsp_var_raw)
glbFeatsInteractionOnly <- list()
#glbFeatsInteractionOnly[["<child_feat>"]] <- "<parent_feat>"
glbFeatsDrop <- c(NULL
# , "<feat1>", "<feat2>"
)
glb_map_vars <- c("MetroAreaCode", "CountryOfBirthCode")
glb_map_urls <- list();
glb_map_urls[["MetroAreaCode"]] <- "https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/MetroAreaCodes.csv"
glb_map_urls[["CountryOfBirthCode"]] <- "https://d37djvu3ytnwxt.cloudfront.net/asset-v1:MITx+15.071x_3+1T2016+type@asset+block/CountryCodes.csv"
# Derived features; Use this mechanism to cleanse data ??? Cons: Data duplication ???
glbFeatsDerive <- list();
# glbFeatsDerive[["<feat.my.sfx>"]] <- list(
# mapfn = function(<arg1>, <arg2>) { return(function(<arg1>, <arg2>)) }
# , args = c("<arg1>", "<arg2>"))
#myprint_df(data.frame(ImageId = mapfn(glbObsAll$.src, glbObsAll$.pos)))
#data.frame(ImageId = mapfn(glbObsAll$.src, glbObsAll$.pos))[7045:7055, ]
# character
glbFeatsDerive[["Education.fctr"]] <- list(
mapfn = function(Education) { raw <- Education; raw[is.na(raw)] <- "NA.my"; return(as.factor(raw)) }
, args = c("Education"))
glbFeatsDerive[["Married.fctr"]] <- list(
mapfn = function(Married) { raw <- Married; raw[is.na(raw)] <- "NA.my"; return(as.factor(raw)) }
, args = c("Married"))
glbFeatsDerive[["MetroArea.fctr"]] <- list(
mapfn = function(MetroArea) { raw <- MetroArea; raw[is.na(raw)] <- "NA.my"; return(as.factor(raw)) }
, args = c("MetroArea"))
# mapfn = function(Week) { return(substr(Week, 1, 10)) }
# mapfn = function(Name) { return(sapply(Name, function(thsName)
# str_sub(unlist(str_split(thsName, ","))[1], 1, 1))) }
# mapfn = function(descriptor) { return(plyr::revalue(descriptor, c(
# "ABANDONED BUILDING" = "OTHER",
# "**" = "**"
# ))) }
# mapfn = function(description) { mod_raw <- description;
# This is here because it does not work if it's in txt_map_filename
# mod_raw <- gsub(paste0(c("\n", "\211", "\235", "\317", "\333"), collapse = "|"), " ", mod_raw)
# Don't parse for "." because of ".com"; use customized gsub for that text
# mod_raw <- gsub("(\\w)(!|\\*|,|-|/)(\\w)", "\\1\\2 \\3", mod_raw);
# Some state acrnoyms need context for separation e.g.
# LA/L.A. could either be "Louisiana" or "LosAngeles"
# modRaw <- gsub("\\bL\\.A\\.( |,|')", "LosAngeles\\1", modRaw);
# OK/O.K. could either be "Oklahoma" or "Okay"
# modRaw <- gsub("\\bACA OK\\b", "ACA OKay", modRaw);
# modRaw <- gsub("\\bNow O\\.K\\.\\b", "Now OKay", modRaw);
# PR/P.R. could either be "PuertoRico" or "Public Relations"
# modRaw <- gsub("\\bP\\.R\\. Campaign", "PublicRelations Campaign", modRaw);
# VA/V.A. could either be "Virginia" or "VeteransAdministration"
# modRaw <- gsub("\\bthe V\\.A\\.\\:", "the VeteranAffairs:", modRaw);
#
# Custom mods
# return(mod_raw) }
# numeric
# Create feature based on record position/id in data
glbFeatsDerive[[".pos"]] <- list(
mapfn = function(.rnorm) { return(1:length(.rnorm)) }
, args = c(".rnorm"))
glbFeatsDerive[[".pos.y"]] <- list(
mapfn = function(.rnorm) { return(1:length(.rnorm)) }
, args = c(".rnorm"))
# Add logs of numerics that are not distributed normally
# Derive & keep multiple transformations of the same feature, if normality is hard to achieve with just one transformation
# Right skew: logp1; sqrt; ^ 1/3; logp1(logp1); log10; exp(-<feat>/constant)
# glbFeatsDerive[["WordCount.log1p"]] <- list(
# mapfn = function(WordCount) { return(log1p(WordCount)) }
# , args = c("WordCount"))
# glbFeatsDerive[["WordCount.root2"]] <- list(
# mapfn = function(WordCount) { return(WordCount ^ (1/2)) }
# , args = c("WordCount"))
# glbFeatsDerive[["WordCount.nexp"]] <- list(
# mapfn = function(WordCount) { return(exp(-WordCount)) }
# , args = c("WordCount"))
#print(summary(glbObsAll$WordCount))
#print(summary(mapfn(glbObsAll$WordCount)))
# If imputation shd be skipped for this feature
# glbFeatsDerive[["District.fctr"]] <- list(
# mapfn = function(District) {
# raw <- District;
# ret_vals <- rep_len("NA", length(raw));
# ret_vals[!is.na(raw)] <- sapply(raw[!is.na(raw)], function(elm)
# ifelse(elm < 10, "1-9",
# ifelse(elm < 20, "10-19", "20+")));
# return(relevel(as.factor(ret_vals), ref = "NA"))
# }
# , args = c("District"))
# If imputation of missing data is not working ...
# glbFeatsDerive[["FertilityRate.nonNA"]] <- list(
# mapfn = function(FertilityRate, Region) {
# RegionMdn <- tapply(FertilityRate, Region, FUN = median, na.rm = TRUE)
#
# retVal <- FertilityRate
# retVal[is.na(FertilityRate)] <- RegionMdn[Region[is.na(FertilityRate)]]
# return(retVal)
# }
# , args = c("FertilityRate", "Region"))
# mapfn = function(HOSPI.COST) { return(cut(HOSPI.COST, 5, breaks = c(0, 100000, 200000, 300000, 900000), labels = NULL)) }
# mapfn = function(Rasmussen) { return(ifelse(sign(Rasmussen) >= 0, 1, 0)) }
# mapfn = function(startprice) { return(startprice ^ (1/2)) }
# mapfn = function(startprice) { return(log(startprice)) }
# mapfn = function(startprice) { return(exp(-startprice / 20)) }
# mapfn = function(startprice) { return(scale(log(startprice))) }
# mapfn = function(startprice) { return(sign(sprice.predict.diff) * (abs(sprice.predict.diff) ^ (1/10))) }
# factor
# mapfn = function(PropR) { return(as.factor(ifelse(PropR >= 0.5, "Y", "N"))) }
# mapfn = function(productline, description) { as.factor(gsub(" ", "", productline)) }
# mapfn = function(purpose) { return(relevel(as.factor(purpose), ref="all_other")) }
# mapfn = function(raw) { tfr_raw <- as.character(cut(raw, 5));
# tfr_raw[is.na(tfr_raw)] <- "NA.my";
# return(as.factor(tfr_raw)) }
# mapfn = function(startprice.log10) { return(cut(startprice.log10, 3)) }
# mapfn = function(startprice.log10) { return(cut(sprice.predict.diff, c(-1000, -100, -10, -1, 0, 1, 10, 100, 1000))) }
# , args = c("<arg1>"))
# multiple args
# mapfn = function(id, date) { return(paste(as.character(id), as.character(date), sep = "#")) }
# mapfn = function(PTS, oppPTS) { return(PTS - oppPTS) }
# mapfn = function(startprice.log10.predict, startprice) {
# return(spdiff <- (10 ^ startprice.log10.predict) - startprice) }
# mapfn = function(productline, description) { as.factor(
# paste(gsub(" ", "", productline), as.numeric(nchar(description) > 0), sep = "*")) }
# mapfn = function(.src, .pos) {
# return(paste(.src, sprintf("%04d",
# ifelse(.src == "Train", .pos, .pos - 7049)
# ), sep = "#")) }
# # If glbObsAll is not sorted in the desired manner
# mapfn=function(Week) { return(coredata(lag(zoo(orderBy(~Week, glbObsAll)$ILI), -2, na.pad=TRUE))) }
# mapfn=function(ILI) { return(coredata(lag(zoo(ILI), -2, na.pad=TRUE))) }
# mapfn=function(ILI.2.lag) { return(log(ILI.2.lag)) }
# glbFeatsDerive[["<var1>"]] <- glbFeatsDerive[["<var2>"]]
# tst <- "descr.my"; args_lst <- NULL; for (arg in glbFeatsDerive[[tst]]$args) args_lst[[arg]] <- glbObsAll[, arg]; print(head(args_lst[[arg]])); print(head(drv_vals <- do.call(glbFeatsDerive[[tst]]$mapfn, args_lst)));
# print(which_ix <- which(args_lst[[arg]] == 0.75)); print(drv_vals[which_ix]);
glbFeatsDateTime <- list()
# Use OlsonNames() to enumerate supported time zones
# glbFeatsDateTime[["<DateTimeFeat>"]] <-
# c(format = "%Y-%m-%d %H:%M:%S" or "%m/%e/%y", timezone = "US/Eastern", impute.na = TRUE,
# last.ctg = FALSE, poly.ctg = FALSE)
glbFeatsPrice <- NULL # or c("<price_var>")
glbFeatsImage <- list() #list(<imageFeat> = list(patchSize = 10)) # if patchSize not specified, no patch computation
glbFeatsText <- list()
Sys.setlocale("LC_ALL", "C") # For english## [1] "C/C/C/C/C/en_US.UTF-8"#glbFeatsText[["<TextFeature>"]] <- list(NULL,
# ,names = myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL,
# <comma-separated-screened-names>
# ))))
# ,rareWords = myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL,
# <comma-separated-nonSCOWL-words>
# ))))
#)
# Text Processing Step: custom modifications not present in txt_munge -> use glbFeatsDerive
# Text Processing Step: universal modifications
glb_txt_munge_filenames_pfx <- "<projectId>_mytxt_"
# Text Processing Step: tolower
# Text Processing Step: myreplacePunctuation
# Text Processing Step: removeWords
glb_txt_stop_words <- list()
# Remember to use unstemmed words
if (length(glbFeatsText) > 0) {
require(tm)
require(stringr)
glb_txt_stop_words[["<txt_var>"]] <- sort(myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# Remove any words from stopwords
# , setdiff(myreplacePunctuation(stopwords("english")), c("<keep_wrd1>", <keep_wrd2>"))
# Remove salutations
,"mr","mrs","dr","Rev"
# Remove misc
#,"th" # Happy [[:digit::]]+th birthday
# Remove terms present in Trn only or New only; search for "Partition post-stem"
# ,<comma-separated-terms>
# cor.y.train == NA
# ,unlist(strsplit(paste(c(NULL
# ,"<comma-separated-terms>"
# ), collapse=",")
# freq == 1; keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
# chisq.pval high (e.g. == 1); keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
# nzv.freqRatio high (e.g. >= glbFeatsNzvFreqMax); keep c("<comma-separated-terms-to-keep>")
# ,<comma-separated-terms>
)))))
}
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^man", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
#glbObsAll[glb_post_stem_words_terms_mtrx_lst[[txtFeat]][, 4866] > 0, c(glb_rsp_var, txtFeat)]
# To identify terms with a specific freq
#paste0(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], freq == 1)$term), collapse = ",")
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], freq <= 2)$term), collapse = ",")
#subset(glb_post_stem_words_terms_df_lst[[txtFeat]], term %in% c("zinger"))
# To identify terms with a specific freq &
# are not stemmed together later OR is value of color.fctr (e.g. gold)
#paste0(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], (freq == 1) & !(term %in% c("blacked","blemish","blocked","blocks","buying","cables","careful","carefully","changed","changing","chargers","cleanly","cleared","connect","connects","connected","contains","cosmetics","default","defaulting","defective","definitely","describe","described","devices","displays","drop","drops","engravement","excellant","excellently","feels","fix","flawlessly","frame","framing","gentle","gold","guarantee","guarantees","handled","handling","having","install","iphone","iphones","keeped","keeps","known","lights","line","lining","liquid","liquidation","looking","lots","manuals","manufacture","minis","most","mostly","network","networks","noted","opening","operated","performance","performs","person","personalized","photograph","physically","placed","places","powering","pre","previously","products","protection","purchasing","returned","rotate","rotation","running","sales","second","seconds","shipped","shuts","sides","skin","skinned","sticker","storing","thats","theres","touching","unusable","update","updates","upgrade","weeks","wrapped","verified","verify") ))$term), collapse = ",")
#print(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (freq <= 2)))
#glbObsAll[which(terms_mtrx[, 229] > 0), glbFeatsText]
# To identify terms with cor.y == NA
#orderBy(~-freq+term, subset(glb_post_stop_words_terms_df_lst[[txtFeat]], is.na(cor.y)))
#paste(sort(subset(glb_post_stop_words_terms_df_lst[[txtFeat]], is.na(cor.y))[, "term"]), collapse=",")
#orderBy(~-freq+term, subset(glb_post_stem_words_terms_df_lst[[txtFeat]], is.na(cor.y)))
# To identify terms with low cor.y.abs
#head(orderBy(~cor.y.abs+freq+term, subset(glb_post_stem_words_terms_df_lst[[txtFeat]], !is.na(cor.y))), 5)
# To identify terms with high chisq.pval
#subset(glb_post_stem_words_terms_df_lst[[txtFeat]], chisq.pval > 0.99)
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (chisq.pval > 0.99) & (freq <= 10))$term), collapse=",")
#paste0(sort(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (chisq.pval > 0.9))$term), collapse=",")
#head(orderBy(~-chisq.pval+freq+term, glb_post_stem_words_terms_df_lst[[txtFeat]]), 5)
#glbObsAll[glb_post_stem_words_terms_mtrx_lst[[txtFeat]][, 68] > 0, glbFeatsText]
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^m", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
# To identify terms with high nzv.freqRatio
#summary(glb_post_stem_words_terms_df_lst[[txtFeat]]$nzv.freqRatio)
#paste0(sort(setdiff(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], (nzv.freqRatio >= glbFeatsNzvFreqMax) & (freq < 10) & (chisq.pval >= 0.05))$term, c( "128gb","3g","4g","gold","ipad1","ipad3","ipad4","ipadair2","ipadmini2","manufactur","spacegray","sprint","tmobil","verizon","wifion"))), collapse=",")
# To identify obs with a txt term
#tail(orderBy(~-freq+term, glb_post_stop_words_terms_df_lst[[txtFeat]]), 20)
#mydspObs(list(descr.my.contains="non"), cols=c("color", "carrier", "cellular", "storage"))
#grep("ever", dimnames(terms_stop_mtrx)$Terms)
#which(terms_stop_mtrx[, grep("ipad", dimnames(terms_stop_mtrx)$Terms)] > 0)
#glbObsAll[which(terms_stop_mtrx[, grep("16", dimnames(terms_stop_mtrx)$Terms)[1]] > 0), c(glbFeatsCategory, "storage", txtFeat)]
# Text Processing Step: screen for names # Move to glbFeatsText specs section in order of text processing steps
# glbFeatsText[["<txtFeat>"]]$names <- myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# # Person names for names screening
# ,<comma-separated-list>
#
# # Company names
# ,<comma-separated-list>
#
# # Product names
# ,<comma-separated-list>
# ))))
# glbFeatsText[["<txtFeat>"]]$rareWords <- myreplacePunctuation(str_to_lower(gsub(" ", "", c(NULL
# # Words not in SCOWL db
# ,<comma-separated-list>
# ))))
# To identify char vectors post glbFeatsTextMap
#grep("six(.*)hour", glb_txt_chr_lst[[txtFeat]], ignore.case = TRUE, value = TRUE)
#grep("[S|s]ix(.*)[H|h]our", glb_txt_chr_lst[[txtFeat]], value = TRUE)
# To identify whether terms shd be synonyms
#orderBy(~term, glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^moder", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ])
# term_row_df <- glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^came$", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ]
#
# cor(glb_post_stop_words_terms_mtrx_lst[[txtFeat]][glbObsAll$.lcn == "Fit", term_row_df$pos], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
# To identify which stopped words are "close" to a txt term
#sort(cluster_vars)
# Text Processing Step: stemDocument
# To identify stemmed txt terms
#glb_post_stop_words_terms_df_lst[[txtFeat]][grep("^la$", glb_post_stop_words_terms_df_lst[[txtFeat]]$term), ]
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^con", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
#glbObsAll[which(terms_stem_mtrx[, grep("use", dimnames(terms_stem_mtrx)$Terms)[[1]]] > 0), c(glbFeatsId, "productline", txtFeat)]
#glbObsAll[which(TfIdf_stem_mtrx[, 191] > 0), c(glbFeatsId, glbFeatsCategory, txtFeat)]
#glbObsAll[which(glb_post_stop_words_terms_mtrx_lst[[txtFeat]][, 6165] > 0), c(glbFeatsId, glbFeatsCategory, txtFeat)]
#which(glbObsAll$UniqueID %in% c(11915, 11926, 12198))
# Text Processing Step: mycombineSynonyms
# To identify which terms are associated with not -> combine "could not" & "couldn't"
#findAssocs(glb_full_DTM_lst[[txtFeat]], "not", 0.05)
# To identify which synonyms should be combined
#orderBy(~term, glb_post_stem_words_terms_df_lst[[txtFeat]][grep("^c", glb_post_stem_words_terms_df_lst[[txtFeat]]$term), ])
chk_comb_cor <- function(syn_lst) {
# cor(terms_stem_mtrx[glbObsAll$.src == "Train", grep("^(damag|dent|ding)$", dimnames(terms_stem_mtrx)[[2]])], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
print(subset(glb_post_stem_words_terms_df_lst[[txtFeat]], term %in% syn_lst$syns))
print(subset(get_corpus_terms(tm_map(glbFeatsTextCorpus[[txtFeat]], mycombineSynonyms, list(syn_lst), lazy=FALSE)), term == syn_lst$word))
# cor(terms_stop_mtrx[glbObsAll$.src == "Train", grep("^(damage|dent|ding)$", dimnames(terms_stop_mtrx)[[2]])], glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
# cor(rowSums(terms_stop_mtrx[glbObsAll$.src == "Train", grep("^(damage|dent|ding)$", dimnames(terms_stop_mtrx)[[2]])]), glbObsTrn[, glb_rsp_var], use="pairwise.complete.obs")
}
#chk_comb_cor(syn_lst=list(word="cabl", syns=c("cabl", "cord")))
#chk_comb_cor(syn_lst=list(word="damag", syns=c("damag", "dent", "ding")))
#chk_comb_cor(syn_lst=list(word="dent", syns=c("dent", "ding")))
#chk_comb_cor(syn_lst=list(word="use", syns=c("use", "usag")))
glbFeatsTextSynonyms <- list()
# list parsed to collect glbFeatsText[[<txtFeat>]]$vldTerms
# glbFeatsTextSynonyms[["Hdln.my"]] <- list(NULL
# # people in places
# , list(word = "australia", syns = c("australia", "australian"))
# , list(word = "italy", syns = c("italy", "Italian"))
# , list(word = "newyork", syns = c("newyork", "newyorker"))
# , list(word = "Pakistan", syns = c("Pakistan", "Pakistani"))
# , list(word = "peru", syns = c("peru", "peruvian"))
# , list(word = "qatar", syns = c("qatar", "qatari"))
# , list(word = "scotland", syns = c("scotland", "scotish"))
# , list(word = "Shanghai", syns = c("Shanghai", "Shanzhai"))
# , list(word = "venezuela", syns = c("venezuela", "venezuelan"))
#
# # companies - needs to be data dependent
# # - e.g. ensure BNP in this experiment/feat always refers to BNPParibas
#
# # general synonyms
# , list(word = "Create", syns = c("Create","Creator"))
# , list(word = "cute", syns = c("cute","cutest"))
# , list(word = "Disappear", syns = c("Disappear","Fadeout"))
# , list(word = "teach", syns = c("teach", "taught"))
# , list(word = "theater", syns = c("theater", "theatre", "theatres"))
# , list(word = "understand", syns = c("understand", "understood"))
# , list(word = "weak", syns = c("weak", "weaken", "weaker", "weakest"))
# , list(word = "wealth", syns = c("wealth", "wealthi"))
#
# # custom synonyms (phrases)
#
# # custom synonyms (names)
# )
#glbFeatsTextSynonyms[["<txtFeat>"]] <- list(NULL
# , list(word="<stem1>", syns=c("<stem1>", "<stem1_2>"))
# )
for (txtFeat in names(glbFeatsTextSynonyms))
for (entryIx in 1:length(glbFeatsTextSynonyms[[txtFeat]])) {
glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$word <-
str_to_lower(glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$word)
glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$syns <-
str_to_lower(glbFeatsTextSynonyms[[txtFeat]][[entryIx]]$syns)
}
glbFeatsTextSeed <- 181
# tm options include: check tm::weightSMART
glb_txt_terms_control <- list( # Gather model performance & run-time stats
# weighting = function(x) weightSMART(x, spec = "nnn")
# weighting = function(x) weightSMART(x, spec = "lnn")
# weighting = function(x) weightSMART(x, spec = "ann")
# weighting = function(x) weightSMART(x, spec = "bnn")
# weighting = function(x) weightSMART(x, spec = "Lnn")
#
weighting = function(x) weightSMART(x, spec = "ltn") # default
# weighting = function(x) weightSMART(x, spec = "lpn")
#
# weighting = function(x) weightSMART(x, spec = "ltc")
#
# weighting = weightBin
# weighting = weightTf
# weighting = weightTfIdf # : default
# termFreq selection criteria across obs: tm default: list(global=c(1, Inf))
, bounds = list(global = c(1, Inf))
# wordLengths selection criteria: tm default: c(3, Inf)
, wordLengths = c(1, Inf)
)
glb_txt_cor_var <- glb_rsp_var # : default # or c(<feat>)
# select one from c("union.top.val.cor", "top.cor", "top.val", default: "top.chisq", "sparse")
glbFeatsTextFilter <- "top.chisq"
glbFeatsTextTermsMax <- rep(10, length(glbFeatsText)) # :default
names(glbFeatsTextTermsMax) <- names(glbFeatsText)
# Text Processing Step: extractAssoc
glbFeatsTextAssocCor <- rep(1, length(glbFeatsText)) # :default
names(glbFeatsTextAssocCor) <- names(glbFeatsText)
# Remember to use stemmed terms
glb_important_terms <- list()
# Text Processing Step: extractPatterns (ngrams)
glbFeatsTextPatterns <- list()
#glbFeatsTextPatterns[[<txtFeat>>]] <- list()
#glbFeatsTextPatterns[[<txtFeat>>]] <- c(metropolitan.diary.colon = "Metropolitan Diary:")
# Have to set it even if it is not used
# Properties:
# numrows(glb_feats_df) << numrows(glbObsFit
# Select terms that appear in at least 0.2 * O(FP/FN(glbObsOOB)) ???
# numrows(glbObsOOB) = 1.1 * numrows(glbObsNew) ???
glb_sprs_thresholds <- NULL # or c(<txtFeat1> = 0.988, <txtFeat2> = 0.970, <txtFeat3> = 0.970)
glbFctrMaxUniqVals <- 20 # default: 20
glb_impute_na_data <- FALSE # or TRUE
glb_mice_complete.seed <- 144 # or any integer
glb_cluster <- FALSE # : default or TRUE
glb_cluster.seed <- 189 # or any integer
glb_cluster_entropy_var <- NULL # c(glb_rsp_var, as.factor(cut(glb_rsp_var, 3)), default: NULL)
glbFeatsTextClusterVarsExclude <- FALSE # default FALSE
glb_interaction_only_feats <- NULL # : default or c(<parent_feat> = "<child_feat>")
glbFeatsNzvFreqMax <- 19 # 19 : caret default
glbFeatsNzvUniqMin <- 10 # 10 : caret default
glbRFESizes <- list()
#glbRFESizes[["mdlFamily"]] <- c(4, 8, 16, 32, 64, 67, 68, 69) # Accuracy@69/70 = 0.8258
glbObsFitOutliers <- list()
# If outliers.n >= 10; consider concatenation of interaction vars
# glbObsFitOutliers[["<mdlFamily>"]] <- c(NULL
# is.na(.rstudent)
# max(.rstudent)
# is.na(.dffits)
# .hatvalues >= 0.99
# -38,167,642 < minmax(.rstudent) < 49,649,823
# , <comma-separated-<glbFeatsId>>
# )
glbObsTrnOutliers <- list()
glbObsTrnOutliers[["Final"]] <- union(glbObsFitOutliers[["All.X"]],
c(NULL
))
# influence.measures: car::outlier; rstudent; dffits; hatvalues; dfbeta; dfbetas
#mdlId <- "All.X##rcv#glm"; obs_df <- fitobs_df
#mdlId <- "RFE.X.glm"; obs_df <- fitobs_df
#mdlId <- "Final.glm"; obs_df <- trnobs_df
#mdlId <- "CSM2.X.glm"; obs_df <- fitobs_df
#print(outliers <- car::outlierTest(glb_models_lst[[mdlId]]$finalModel))
#mdlIdFamily <- paste0(head(unlist(str_split(mdlId, "\\.")), -1), collapse="."); obs_df <- dplyr::filter_(obs_df, interp(~(!(var %in% glbObsFitOutliers[[mdlIdFamily]])), var = as.name(glbFeatsId))); model_diags_df <- cbind(obs_df, data.frame(.rstudent=stats::rstudent(glb_models_lst[[mdlId]]$finalModel)), data.frame(.dffits=stats::dffits(glb_models_lst[[mdlId]]$finalModel)), data.frame(.hatvalues=stats::hatvalues(glb_models_lst[[mdlId]]$finalModel)));print(summary(model_diags_df[, c(".rstudent",".dffits",".hatvalues")])); table(cut(model_diags_df$.hatvalues, breaks=c(0.00, 0.98, 0.99, 1.00)))
#print(subset(model_diags_df, is.na(.rstudent))[, glbFeatsId])
#print(model_diags_df[which.max(model_diags_df$.rstudent), ])
#print(subset(model_diags_df, is.na(.dffits))[, glbFeatsId])
#print(model_diags_df[which.min(model_diags_df$.dffits), ])
#print(subset(model_diags_df, .hatvalues > 0.99)[, glbFeatsId])
#dffits_df <- merge(dffits_df, outliers_df, by="row.names", all.x=TRUE); row.names(dffits_df) <- dffits_df$Row.names; dffits_df <- subset(dffits_df, select=-Row.names)
#dffits_df <- merge(dffits_df, glbObsFit, by="row.names", all.x=TRUE); row.names(dffits_df) <- dffits_df$Row.names; dffits_df <- subset(dffits_df, select=-Row.names)
#subset(dffits_df, !is.na(.Bonf.p))
#mdlId <- "CSM.X.glm"; vars <- myextract_actual_feats(row.names(orderBy(reformulate(c("-", paste0(mdlId, ".imp"))), myget_feats_imp(glb_models_lst[[mdlId]]))));
#model_diags_df <- glb_get_predictions(model_diags_df, mdlId, glb_rsp_var)
#obs_ix <- row.names(model_diags_df) %in% names(outliers$rstudent)[1]
#obs_ix <- which(is.na(model_diags_df$.rstudent))
#obs_ix <- which(is.na(model_diags_df$.dffits))
#myplot_parcoord(obs_df=model_diags_df[, c(glbFeatsId, glbFeatsCategory, ".rstudent", ".dffits", ".hatvalues", glb_rsp_var, paste0(glb_rsp_var, mdlId), vars[1:min(20, length(vars))])], obs_ix=obs_ix, id_var=glbFeatsId, category_var=glbFeatsCategory)
#model_diags_df[row.names(model_diags_df) %in% names(outliers$rstudent)[c(1:2)], ]
#ctgry_diags_df <- model_diags_df[model_diags_df[, glbFeatsCategory] %in% c("Unknown#0"), ]
#myplot_parcoord(obs_df=ctgry_diags_df[, c(glbFeatsId, glbFeatsCategory, ".rstudent", ".dffits", ".hatvalues", glb_rsp_var, "startprice.log10.predict.RFE.X.glmnet", indepVar[1:20])], obs_ix=row.names(ctgry_diags_df) %in% names(outliers$rstudent)[1], id_var=glbFeatsId, category_var=glbFeatsCategory)
#table(glbObsFit[model_diags_df[, glbFeatsCategory] %in% c("iPad1#1"), "startprice.log10.cut.fctr"])
#glbObsFit[model_diags_df[, glbFeatsCategory] %in% c("iPad1#1"), c(glbFeatsId, "startprice")]
# No outliers & .dffits == NaN
#myplot_parcoord(obs_df=model_diags_df[, c(glbFeatsId, glbFeatsCategory, glb_rsp_var, "startprice.log10.predict.RFE.X.glmnet", indepVar[1:10])], obs_ix=seq(1:nrow(model_diags_df))[is.na(model_diags_df$.dffits)], id_var=glbFeatsId, category_var=glbFeatsCategory)
# Modify mdlId to (build & extract) "<FamilyId>#<Fit|Trn>#<caretMethod>#<preProc1.preProc2>#<samplingMethod>"
glb_models_lst <- list(); glb_models_df <- data.frame()
# Add xgboost algorithm
# Regression
if (glb_is_regression) {
glbMdlMethods <- c(NULL
# deterministic
#, "lm", # same as glm
, "glm", "bayesglm", "glmnet"
, "rpart"
# non-deterministic
, "gbm", "rf"
# Unknown
, "nnet" , "avNNet" # runs 25 models per cv sample for tunelength=5
, "svmLinear", "svmLinear2"
, "svmPoly" # runs 75 models per cv sample for tunelength=5
, "svmRadial"
, "earth"
, "bagEarth" # Takes a long time
)
} else
# Classification - Add ada (auto feature selection)
if (glb_is_binomial)
glbMdlMethods <- c(NULL
# deterministic
, "bagEarth" # Takes a long time
, "glm", "bayesglm", "glmnet"
, "nnet"
, "rpart"
# non-deterministic
, "gbm"
, "avNNet" # runs 25 models per cv sample for tunelength=5
, "rf"
# Unknown
, "lda", "lda2"
# svm models crash when predict is called -> internal to kernlab it should call predict without .outcome
, "svmLinear", "svmLinear2"
, "svmPoly" # runs 75 models per cv sample for tunelength=5
, "svmRadial"
, "earth"
) else
glbMdlMethods <- c(NULL
# deterministic
,"glmnet"
# non-deterministic
,"rf"
# Unknown
,"gbm","rpart"
)
glbMdlFamilies <- list(); glb_mdl_feats_lst <- list()
# family: Choose from c("RFE.X", "CSM.X", "All.X", "Best.Interact")
# methods: Choose from c(NULL, <method>, glbMdlMethods)
#glbMdlFamilies[["RFE.X"]] <- c("glmnet", "glm") # non-NULL vector is mandatory
if (glb_is_classification && !glb_is_binomial)
# glm does not work for multinomial
glbMdlFamilies[["All.X"]] <- c("glmnet") else
glbMdlFamilies[["All.X"]] <- c("glmnet", "glm")
#glbMdlFamilies[["Best.Interact"]] <- "glmnet" # non-NULL vector is mandatory
# Check if interaction features make RFE better
# glbMdlFamilies[["CSM.X"]] <- setdiff(glbMdlMethods, c("lda", "lda2")) # crashing due to category:.clusterid ??? #c("glmnet", "glm") # non-NULL list is mandatory
# glb_mdl_feats_lst[["CSM.X"]] <- c(NULL
# , <comma-separated-features-vector>
# )
# dAFeats.CSM.X %<d-% c(NULL
# # Interaction feats up to varImp(RFE.X.glmnet) >= 50
# , <comma-separated-features-vector>
# , setdiff(myextract_actual_feats(predictors(rfe_fit_results)), c(NULL
# , <comma-separated-features-vector>
# ))
# )
# glb_mdl_feats_lst[["CSM.X"]] <- "%<d-% dAFeats.CSM.X"
glbMdlFamilies[["Final"]] <- c(NULL) # NULL vector acceptable # c("glmnet", "glm")
glbMdlAllowParallel <- list()
#glbMdlAllowParallel[["<mdlId>"]] <- FALSE
glbMdlAllowParallel[["Max.cor.Y##rcv#rpart"]] <- FALSE
glbMdlAllowParallel[["All.X##rcv#glmnet"]] <- FALSE
glbMdlAllowParallel[["All.X##rcv#glm"]] <- FALSE
glbMdlAllowParallel[["Final.All.X##rcv#glmnet"]] <- FALSE
glbMdlAllowParallel[["Final.X##rcv#glmnet"]] <- FALSE
glbMdlAllowParallel[["Final##rcv#glmnet"]] <- FALSE
# Check if tuning parameters make fit better; make it mdlFamily customizable ?
glbMdlTuneParams <- data.frame()
# When glmnet crashes at model$grid with error: ???
glmnetTuneParams <- rbind(data.frame()
,data.frame(parameter = "alpha", vals = "0.100 0.325 0.550 0.775 1.000")
,data.frame(parameter = "lambda", vals = "9.342e-02")
)
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams,
# cbind(data.frame(mdlId = "<mdlId>"),
# glmnetTuneParams))
#avNNet
# size=[1] 3 5 7 9; decay=[0] 1e-04 0.001 0.01 0.1; bag=[FALSE]; RMSE=1.3300906
#bagEarth
# degree=1 [2] 3; nprune=64 128 256 512 [1024]; RMSE=0.6486663 (up)
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "bagEarth", parameter = "nprune", vals = "256")
# ,data.frame(method = "bagEarth", parameter = "degree", vals = "2")
# ))
#earth
# degree=[1]; nprune=2 [9] 17 25 33; RMSE=0.1334478
#gbm
# shrinkage=0.05 [0.10] 0.15 0.20 0.25; n.trees=100 150 200 [250] 300; interaction.depth=[1] 2 3 4 5; n.minobsinnode=[10]; RMSE=0.2008313
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "gbm", parameter = "shrinkage", min = 0.05, max = 0.25, by = 0.05)
# ,data.frame(method = "gbm", parameter = "n.trees", min = 100, max = 300, by = 50)
# ,data.frame(method = "gbm", parameter = "interaction.depth", min = 1, max = 5, by = 1)
# ,data.frame(method = "gbm", parameter = "n.minobsinnode", min = 10, max = 10, by = 10)
# #seq(from=0.05, to=0.25, by=0.05)
# ))
#glmnet
# alpha=0.100 [0.325] 0.550 0.775 1.000; lambda=0.0005232693 0.0024288010 0.0112734954 [0.0523269304] 0.2428800957; RMSE=0.6164891
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "glmnet", parameter = "alpha", vals = "0.550 0.775 0.8875 0.94375 1.000")
# ,data.frame(method = "glmnet", parameter = "lambda", vals = "9.858855e-05 0.0001971771 0.0009152152 0.0042480525 0.0197177130")
# ))
#nnet
# size=3 5 [7] 9 11; decay=0.0001 0.001 0.01 [0.1] 0.2; RMSE=0.9287422
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "nnet", parameter = "size", vals = "3 5 7 9 11")
# ,data.frame(method = "nnet", parameter = "decay", vals = "0.0001 0.0010 0.0100 0.1000 0.2000")
# ))
#rf # Don't bother; results are not deterministic
# mtry=2 35 68 [101] 134; RMSE=0.1339974
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "rf", parameter = "mtry", vals = "2 5 9 13 17")
# ))
#rpart
# cp=0.020 [0.025] 0.030 0.035 0.040; RMSE=0.1770237
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "rpart", parameter = "cp", vals = "0.004347826 0.008695652 0.017391304 0.021739130 0.034782609")
# ))
#svmLinear
# C=0.01 0.05 [0.10] 0.50 1.00 2.00 3.00 4.00; RMSE=0.1271318; 0.1296718
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "svmLinear", parameter = "C", vals = "0.01 0.05 0.1 0.5 1")
# ))
#svmLinear2
# cost=0.0625 0.1250 [0.25] 0.50 1.00; RMSE=0.1276354
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method = "svmLinear2", parameter = "cost", vals = "0.0625 0.125 0.25 0.5 1")
# ))
#svmPoly
# degree=[1] 2 3 4 5; scale=0.01 0.05 [0.1] 0.5 1; C=0.50 1.00 [2.00] 3.00 4.00; RMSE=0.1276130
# glbMdlTuneParams <- myrbind_df(glbMdlTuneParams, rbind(data.frame()
# ,data.frame(method="svmPoly", parameter="degree", min=1, max=5, by=1) #seq(1, 5, 1)
# ,data.frame(method="svmPoly", parameter="scale", vals="0.01, 0.05, 0.1, 0.5, 1")
# ,data.frame(method="svmPoly", parameter="C", vals="0.50, 1.00, 2.00, 3.00, 4.00")
# ))
#svmRadial
# sigma=[0.08674323]; C=0.25 0.50 1.00 [2.00] 4.00; RMSE=0.1614957
#glb2Sav(); all.equal(sav_models_df, glb_models_df)
glb_preproc_methods <- NULL
# c("YeoJohnson", "center.scale", "range", "pca", "ica", "spatialSign")
# Baseline prediction model feature(s)
glb_Baseline_mdl_var <- NULL # or c("<feat>")
glbMdlMetric_terms <- NULL # or matrix(c(
# 0,1,2,3,4,
# 2,0,1,2,3,
# 4,2,0,1,2,
# 6,4,2,0,1,
# 8,6,4,2,0
# ), byrow=TRUE, nrow=5)
glbMdlMetricSummary <- NULL # or "<metric_name>"
glbMdlMetricMaximize <- NULL # or FALSE (TRUE is not the default for both classification & regression)
glbMdlMetricSummaryFn <- NULL # or function(data, lev=NULL, model=NULL) {
# confusion_mtrx <- t(as.matrix(confusionMatrix(data$pred, data$obs)))
# #print(confusion_mtrx)
# #print(confusion_mtrx * glbMdlMetric_terms)
# metric <- sum(confusion_mtrx * glbMdlMetric_terms) / nrow(data)
# names(metric) <- glbMdlMetricSummary
# return(metric)
# }
glbMdlCheckRcv <- FALSE # Turn it on when needed; otherwise takes long time
glb_rcv_n_folds <- 3 # or NULL
glb_rcv_n_repeats <- 3 # or NULL
glb_clf_proba_threshold <- NULL # 0.5
# Model selection criteria
if (glb_is_regression)
glbMdlMetricsEval <- c("min.RMSE.OOB", "max.R.sq.OOB", "max.Adj.R.sq.fit", "min.RMSE.fit")
#glbMdlMetricsEval <- c("min.RMSE.fit", "max.R.sq.fit", "max.Adj.R.sq.fit")
if (glb_is_classification) {
if (glb_is_binomial)
glbMdlMetricsEval <-
c("max.Accuracy.OOB", "max.AUCROCR.OOB", "max.AUCpROC.OOB", "min.aic.fit", "max.Accuracy.fit") else
glbMdlMetricsEval <- c("max.Accuracy.OOB", "max.Kappa.OOB")
}
# select from NULL [no ensemble models], "auto" [all models better than MFO or Baseline], c(mdl_ids in glb_models_lst) [Typically top-rated models in auto]
glb_mdl_ensemble <- NULL
# "%<d-% setdiff(mygetEnsembleAutoMdlIds(), 'CSM.X.rf')"
# c(<comma-separated-mdlIds>
# )
# Only for classifications; for regressions remove "(.*)\\.prob" form the regex
# tmp_fitobs_df <- glbObsFit[, grep(paste0("^", gsub(".", "\\.", mygetPredictIds$value, fixed = TRUE), "CSM\\.X\\.(.*)\\.prob"), names(glbObsFit), value = TRUE)]; cor_mtrx <- cor(tmp_fitobs_df); cor_vctr <- sort(cor_mtrx[row.names(orderBy(~-Overall, varImp(glb_models_lst[["Ensemble.repeatedcv.glmnet"]])$imp))[1], ]); summary(cor_vctr); cor_vctr
#ntv.glm <- glm(reformulate(indepVar, glb_rsp_var), family = "binomial", data = glbObsFit)
#step.glm <- step(ntv.glm)
glb_sel_mdl_id <- "All.X##rcv#glmnet" #select from c(NULL, "All.X##rcv#glmnet", "RFE.X##rcv#glmnet", <mdlId>)
glb_fin_mdl_id <- NULL #select from c(NULL, glb_sel_mdl_id)
glb_dsp_cols <- c(".pos", glbFeatsId, glbFeatsCategory, glb_rsp_var
# List critical cols excl. above
)
# Output specs
# lclgetfltout_df <- function(obsout_df) {
# require(tidyr)
# obsout_df <- obsout_df %>%
# tidyr::separate("ImageId.x.y", c(".src", ".pos", "x", "y"),
# sep = "#", remove = TRUE, extra = "merge")
# # mnm prefix stands for max_n_mean
# mnmout_df <- obsout_df %>%
# dplyr::group_by(.pos) %>%
# #dplyr::top_n(1, Probability1) %>% # Score = 3.9426
# #dplyr::top_n(2, Probability1) %>% # Score = ???; weighted = 3.94254;
# #dplyr::top_n(3, Probability1) %>% # Score = 3.9418; weighted = 3.94169;
# dplyr::top_n(4, Probability1) %>% # Score = ???; weighted = 3.94149;
# #dplyr::top_n(5, Probability1) %>% # Score = 3.9421; weighted = 3.94178
#
# # dplyr::summarize(xMeanN = mean(as.numeric(x)), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), Probability1), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1, 0.2357323, 0.2336925)), yMeanN = mean(as.numeric(y)))
# # dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1)), yMeanN = mean(as.numeric(y)))
# dplyr::summarize(xMeanN = weighted.mean(as.numeric(x), c(Probability1)),
# yMeanN = weighted.mean(as.numeric(y), c(Probability1)))
#
# maxout_df <- obsout_df %>%
# dplyr::group_by(.pos) %>%
# dplyr::summarize(maxProb1 = max(Probability1))
# fltout_df <- merge(maxout_df, obsout_df,
# by.x = c(".pos", "maxProb1"), by.y = c(".pos", "Probability1"),
# all.x = TRUE)
# fmnout_df <- merge(fltout_df, mnmout_df,
# by.x = c(".pos"), by.y = c(".pos"),
# all.x = TRUE)
# return(fmnout_df)
# }
glbObsOut <- list(NULL
# glbFeatsId will be the first output column, by default
,vars = list()
# ,mapFn = function(obsout_df) {
# }
)
#obsout_df <- savobsout_df
# glbObsOut$mapFn <- function(obsout_df) {
# txfout_df <- dplyr::select(obsout_df, -.pos.y) %>%
# dplyr::mutate(
# lunch = levels(glbObsTrn[, "lunch" ])[
# round(mean(as.numeric(glbObsTrn[, "lunch" ])), 0)],
# dinner = levels(glbObsTrn[, "dinner" ])[
# round(mean(as.numeric(glbObsTrn[, "dinner" ])), 0)],
# reserve = levels(glbObsTrn[, "reserve" ])[
# round(mean(as.numeric(glbObsTrn[, "reserve" ])), 0)],
# outdoor = levels(glbObsTrn[, "outdoor" ])[
# round(mean(as.numeric(glbObsTrn[, "outdoor" ])), 0)],
# expensive = levels(glbObsTrn[, "expensive"])[
# round(mean(as.numeric(glbObsTrn[, "expensive"])), 0)],
# liquor = levels(glbObsTrn[, "liquor" ])[
# round(mean(as.numeric(glbObsTrn[, "liquor" ])), 0)],
# table = levels(glbObsTrn[, "table" ])[
# round(mean(as.numeric(glbObsTrn[, "table" ])), 0)],
# classy = levels(glbObsTrn[, "classy" ])[
# round(mean(as.numeric(glbObsTrn[, "classy" ])), 0)],
# kids = levels(glbObsTrn[, "kids" ])[
# round(mean(as.numeric(glbObsTrn[, "kids" ])), 0)]
# )
#
# print("ObsNew output class tables:")
# print(sapply(c("lunch","dinner","reserve","outdoor",
# "expensive","liquor","table",
# "classy","kids"),
# function(feat) table(txfout_df[, feat], useNA = "ifany")))
#
# txfout_df <- txfout_df %>%
# dplyr::mutate(labels = "") %>%
# dplyr::mutate(labels =
# ifelse(lunch != "-1", paste(labels, lunch ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(dinner != "-1", paste(labels, dinner ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(reserve != "-1", paste(labels, reserve ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(outdoor != "-1", paste(labels, outdoor ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(expensive != "-1", paste(labels, expensive), labels)) %>%
# dplyr::mutate(labels =
# ifelse(liquor != "-1", paste(labels, liquor ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(table != "-1", paste(labels, table ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(classy != "-1", paste(labels, classy ), labels)) %>%
# dplyr::mutate(labels =
# ifelse(kids != "-1", paste(labels, kids ), labels)) %>%
# dplyr::select(business_id, labels)
# return(txfout_df)
# }
#if (!is.null(glbObsOut$mapFn)) obsout_df <- glbObsOut$mapFn(obsout_df); print(head(obsout_df))
glb_out_obs <- NULL # select from c(NULL : default to "new", "all", "new", "trn")
if (glb_is_classification && glb_is_binomial) {
glbObsOut$vars[["Probability1"]] <-
"%<d-% glbObsNew[, mygetPredictIds(glb_rsp_var, glb_fin_mdl_id)$prob]"
# glbObsOut$vars[[glb_rsp_var_raw]] <-
# "%<d-% glb_map_rsp_var_to_raw(glbObsNew[,
# mygetPredictIds(glb_rsp_var, glb_fin_mdl_id)$value])"
} else {
# glbObsOut$vars[[glbFeatsId]] <-
# "%<d-% as.integer(gsub('Test#', '', glbObsNew[, glbFeatsId]))"
glbObsOut$vars[[glb_rsp_var]] <-
"%<d-% glbObsNew[, mygetPredictIds(glb_rsp_var, glb_fin_mdl_id)$value]"
# for (outVar in setdiff(glbFeatsExcludeLcl, glb_rsp_var_raw))
# glbObsOut$vars[[outVar]] <-
# paste0("%<d-% mean(glbObsAll[, \"", outVar, "\"], na.rm = TRUE)")
}
# glbObsOut$vars[[glb_rsp_var_raw]] <- glb_rsp_var_raw
# glbObsOut$vars[[paste0(head(unlist(strsplit(mygetPredictIds$value, "")), -1), collapse = "")]] <-
glbOutStackFnames <- NULL #: default
# c("ebayipads_txt_assoc1_out_bid1_stack.csv") # manual stack
# c("ebayipads_finmdl_bid1_out_nnet_1.csv") # universal stack
glbOut <- list(pfx = "us_cps_2016_")
# lclImageSampleSeed <- 129
glbOutDataVizFname <- NULL # choose from c(NULL, "<projectId>_obsall.csv")
glbChunks <- list(labels = c("set_global_options_wd","set_global_options"
,"import.data","inspect.data","scrub.data","transform.data"
,"extract.features"
,"extract.features.datetime","extract.features.image","extract.features.price"
,"extract.features.text","extract.features.string"
,"extract.features.end"
,"manage.missing.data","cluster.data","partition.data.training","select.features"
,"fit.models_0","fit.models_1","fit.models_2","fit.models_3"
,"fit.data.training_0","fit.data.training_1"
,"predict.data.new"
,"display.session.info"))
# To ensure that all chunks in this script are in glbChunks
if (!is.null(chkChunksLabels <- knitr::all_labels()) && # knitr::all_labels() doesn't work in console runs
!identical(chkChunksLabels, glbChunks$labels)) {
print(sprintf("setdiff(chkChunksLabels, glbChunks$labels): %s",
setdiff(chkChunksLabels, glbChunks$labels)))
print(sprintf("setdiff(glbChunks$labels, chkChunksLabels): %s",
setdiff(glbChunks$labels, chkChunksLabels)))
}
glbChunks[["first"]] <- NULL #default: script will load envir from previous chunk
glbChunks[["last"]] <- NULL #"extract.features.end" #NULL #default: script will save envir at end of this chunk
#mysavChunk(glbOut$pfx, glbChunks[["last"]])
# Inspect max OOB FP
#chkObsOOB <- subset(glbObsOOB, !label.fctr.All.X..rcv.glmnet.is.acc)
#chkObsOOBFP <- subset(chkObsOOB, label.fctr.All.X..rcv.glmnet == "left_eye_center") %>% dplyr::mutate(Probability1 = label.fctr.All.X..rcv.glmnet.prob) %>% select(-.src, -.pos, -x, -y) %>% lclgetfltout_df() %>% mutate(obj.distance = (((as.numeric(x) - left_eye_center_x.int) ^ 2) + ((as.numeric(y) - left_eye_center_y.int) ^ 2)) ^ 0.5) %>% dplyr::top_n(5, obj.distance) %>% dplyr::top_n(5, -patch.cor)
#
#newImgObs <- glbObsNew[(glbObsNew$ImageId == "Test#0001"), ]; print(newImgObs[which.max(newImgObs$label.fctr.Final..rcv.glmnet.prob), ])
#OOBImgObs <- glbObsOOB[(glbObsOOB$ImageId == "Train#0003"), ]; print(OOBImgObs[which.max(OOBImgObs$label.fctr.All.X..rcv.glmnet.prob), ])
#load("us_cps_2016_extract.features.end.RData", verbose = TRUE)
#mygetImage(which(glbObsAll[, glbFeatsId] == "Train#0003"), names(glbFeatsImage)[1], plot = TRUE, featHighlight = c("left_eye_center_x", "left_eye_center_y"), ovrlHighlight = c(66, 35))
# Depict process
glb_analytics_pn <- petrinet(name = "glb_analytics_pn",
trans_df = data.frame(id = 1:6,
name = c("data.training.all","data.new",
"model.selected","model.final",
"data.training.all.prediction","data.new.prediction"),
x=c( -5,-5,-15,-25,-25,-35),
y=c( -5, 5, 0, 0, -5, 5)
),
places_df=data.frame(id=1:4,
name=c("bgn","fit.data.training.all","predict.data.new","end"),
x=c( -0, -20, -30, -40),
y=c( 0, 0, 0, 0),
M0=c( 3, 0, 0, 0)
),
arcs_df = data.frame(
begin = c("bgn","bgn","bgn",
"data.training.all","model.selected","fit.data.training.all",
"fit.data.training.all","model.final",
"data.new","predict.data.new",
"data.training.all.prediction","data.new.prediction"),
end = c("data.training.all","data.new","model.selected",
"fit.data.training.all","fit.data.training.all","model.final",
"data.training.all.prediction","predict.data.new",
"predict.data.new","data.new.prediction",
"end","end")
))
#print(ggplot.petrinet(glb_analytics_pn))
print(ggplot.petrinet(glb_analytics_pn) + coord_flip())## Loading required package: grid
glb_analytics_avl_objs <- NULL
glb_chunks_df <- myadd_chunk(NULL, "import.data")## label step_major step_minor label_minor bgn end elapsed
## 1 import.data 1 0 0 9.784 NA NAStep 1.0: import data
chunk option: eval=
## [1] "Reading file ./data/CPSData.csv..."
## [1] "dimensions of data in ./data/CPSData.csv: 131,302 rows x 14 cols"
## PeopleInHousehold Region State MetroAreaCode Age Married Sex
## 1 1 South Alabama 26620 85 Widowed Female
## 2 3 South Alabama 13820 21 Never Married Male
## 3 3 South Alabama 13820 37 Never Married Female
## 4 3 South Alabama 13820 18 Never Married Male
## 5 3 South Alabama 26620 52 Widowed Female
## 6 3 South Alabama 26620 24 Never Married Male
## Education Race Hispanic CountryOfBirthCode Citizenship
## 1 Associate degree White 0 57 Citizen, Native
## 2 High school Black 0 57 Citizen, Native
## 3 High school Black 0 57 Citizen, Native
## 4 No high school diploma Black 0 57 Citizen, Native
## 5 Associate degree White 0 57 Citizen, Native
## 6 Bachelor's degree White 0 57 Citizen, Native
## EmploymentStatus Industry
## 1 Retired <NA>
## 2 Unemployed Professional and business services
## 3 Disabled <NA>
## 4 Not in Labor Force <NA>
## 5 Employed Professional and business services
## 6 Employed Educational and health services
## PeopleInHousehold Region State MetroAreaCode Age
## 4535 7 South Arkansas 30780 6
## 20007 1 West Colorado 14500 57
## 66863 3 South Mississippi NA 48
## 95549 6 South Oklahoma NA 17
## 96594 1 West Oregon 38900 85
## 129953 2 West Wyoming NA 54
## Married Sex Education Race Hispanic
## 4535 <NA> Female <NA> Black 0
## 20007 Divorced Male Master's degree White 0
## 66863 Never Married Female No high school diploma Black 0
## 95549 Never Married Male No high school diploma White 0
## 96594 Widowed Female No high school diploma White 0
## 129953 Married Male High school White 0
## CountryOfBirthCode Citizenship EmploymentStatus Industry
## 4535 57 Citizen, Native <NA> <NA>
## 20007 57 Citizen, Native Employed Financial
## 66863 57 Citizen, Native Disabled <NA>
## 95549 57 Citizen, Native Not in Labor Force <NA>
## 96594 57 Citizen, Native Retired <NA>
## 129953 57 Citizen, Native Employed Manufacturing
## PeopleInHousehold Region State MetroAreaCode Age Married
## 131297 5 West Wyoming NA 14 <NA>
## 131298 5 West Wyoming NA 17 Never Married
## 131299 5 West Wyoming NA 37 Divorced
## 131300 3 West Wyoming NA 58 Married
## 131301 3 West Wyoming NA 53 Married
## 131302 3 West Wyoming NA 14 <NA>
## Sex Education Race Hispanic CountryOfBirthCode
## 131297 Male <NA> White 0 57
## 131298 Male No high school diploma White 0 57
## 131299 Male High school White 0 57
## 131300 Male Bachelor's degree White 0 57
## 131301 Female Associate degree White 0 57
## 131302 Female <NA> White 0 57
## Citizenship EmploymentStatus Industry
## 131297 Citizen, Native <NA> <NA>
## 131298 Citizen, Native Not in Labor Force <NA>
## 131299 Citizen, Native Employed Mining
## 131300 Citizen, Native Employed Financial
## 131301 Citizen, Native Not in Labor Force <NA>
## 131302 Citizen, Native <NA> <NA>
## 'data.frame': 131302 obs. of 14 variables:
## $ PeopleInHousehold : int 1 3 3 3 3 3 3 2 2 2 ...
## $ Region : chr "South" "South" "South" "South" ...
## $ State : chr "Alabama" "Alabama" "Alabama" "Alabama" ...
## $ MetroAreaCode : int 26620 13820 13820 13820 26620 26620 26620 33660 33660 26620 ...
## $ Age : int 85 21 37 18 52 24 26 71 43 52 ...
## $ Married : chr "Widowed" "Never Married" "Never Married" "Never Married" ...
## $ Sex : chr "Female" "Male" "Female" "Male" ...
## $ Education : chr "Associate degree" "High school" "High school" "No high school diploma" ...
## $ Race : chr "White" "Black" "Black" "Black" ...
## $ Hispanic : int 0 0 0 0 0 0 0 0 0 0 ...
## $ CountryOfBirthCode: int 57 57 57 57 57 57 57 57 57 57 ...
## $ Citizenship : chr "Citizen, Native" "Citizen, Native" "Citizen, Native" "Citizen, Native" ...
## $ EmploymentStatus : chr "Retired" "Unemployed" "Disabled" "Not in Labor Force" ...
## $ Industry : chr NA "Professional and business services" NA NA ...
## - attr(*, "comment")= chr "glbObsTrn"
## NULL## PeopleInHousehold Region State MetroAreaCode Age Married Sex
## 14 4 South Alabama 26620 2 <NA> Female
## 15 4 South Alabama 26620 4 <NA> Male
## 18 2 South Alabama 13820 13 <NA> Female
## 28 3 South Alabama 33860 2 <NA> Female
## 35 6 South Alabama 33860 3 <NA> Female
## 36 6 South Alabama 33860 11 <NA> Female
## Education Race Hispanic CountryOfBirthCode Citizenship
## 14 <NA> White 0 57 Citizen, Native
## 15 <NA> White 0 57 Citizen, Native
## 18 <NA> Black 0 57 Citizen, Native
## 28 <NA> White 0 57 Citizen, Native
## 35 <NA> Black 0 57 Citizen, Native
## 36 <NA> Black 0 57 Citizen, Native
## EmploymentStatus Industry
## 14 <NA> <NA>
## 15 <NA> <NA>
## 18 <NA> <NA>
## 28 <NA> <NA>
## 35 <NA> <NA>
## 36 <NA> <NA>
## PeopleInHousehold Region State MetroAreaCode Age Married
## 229 3 South Alabama 13820 6 <NA>
## 22928 3 Northeast Connecticut 76450 13 <NA>
## 51143 5 South Louisiana 35380 2 <NA>
## 51529 4 South Louisiana 43340 11 <NA>
## 52960 5 Northeast Maine NA 5 <NA>
## 61204 3 Midwest Michigan 19820 0 <NA>
## Sex Education Race Hispanic CountryOfBirthCode Citizenship
## 229 Female <NA> Black 0 57 Citizen, Native
## 22928 Female <NA> White 1 57 Citizen, Native
## 51143 Female <NA> White 0 57 Citizen, Native
## 51529 Female <NA> Black 0 57 Citizen, Native
## 52960 Female <NA> White 0 57 Citizen, Native
## 61204 Male <NA> White 0 57 Citizen, Native
## EmploymentStatus Industry
## 229 <NA> <NA>
## 22928 <NA> <NA>
## 51143 <NA> <NA>
## 51529 <NA> <NA>
## 52960 <NA> <NA>
## 61204 <NA> <NA>
## PeopleInHousehold Region State MetroAreaCode Age Married Sex
## 131282 5 West Wyoming NA 4 <NA> Female
## 131283 5 West Wyoming NA 9 <NA> Female
## 131285 2 West Wyoming NA 21 Married Male
## 131296 5 West Wyoming NA 10 <NA> Female
## 131297 5 West Wyoming NA 14 <NA> Male
## 131302 3 West Wyoming NA 14 <NA> Female
## Education Race Hispanic CountryOfBirthCode Citizenship
## 131282 <NA> White 0 57 Citizen, Native
## 131283 <NA> White 0 57 Citizen, Native
## 131285 High school White 1 57 Citizen, Native
## 131296 <NA> White 0 57 Citizen, Native
## 131297 <NA> White 0 57 Citizen, Native
## 131302 <NA> White 0 57 Citizen, Native
## EmploymentStatus Industry
## 131282 <NA> <NA>
## 131283 <NA> <NA>
## 131285 <NA> <NA>
## 131296 <NA> <NA>
## 131297 <NA> <NA>
## 131302 <NA> <NA>
## 'data.frame': 25789 obs. of 14 variables:
## $ PeopleInHousehold : int 4 4 2 3 6 6 2 4 3 3 ...
## $ Region : chr "South" "South" "South" "South" ...
## $ State : chr "Alabama" "Alabama" "Alabama" "Alabama" ...
## $ MetroAreaCode : int 26620 26620 13820 33860 33860 33860 26620 33660 13820 13820 ...
## $ Age : int 2 4 13 2 3 11 5 14 5 11 ...
## $ Married : chr NA NA NA NA ...
## $ Sex : chr "Female" "Male" "Female" "Female" ...
## $ Education : chr NA NA NA NA ...
## $ Race : chr "White" "White" "Black" "White" ...
## $ Hispanic : int 0 0 0 0 0 0 0 0 0 0 ...
## $ CountryOfBirthCode: int 57 57 57 57 57 57 57 57 57 57 ...
## $ Citizenship : chr "Citizen, Native" "Citizen, Native" "Citizen, Native" "Citizen, Native" ...
## $ EmploymentStatus : chr NA NA NA NA ...
## $ Industry : chr NA NA NA NA ...
## - attr(*, "comment")= chr "glbObsNew"
## PeopleInHousehold Region State MetroAreaCode Age Married Sex
## 1 1 South Alabama 26620 85 Widowed Female
## 2 3 South Alabama 13820 21 Never Married Male
## 3 3 South Alabama 13820 37 Never Married Female
## 4 3 South Alabama 13820 18 Never Married Male
## 5 3 South Alabama 26620 52 Widowed Female
## 6 3 South Alabama 26620 24 Never Married Male
## Education Race Hispanic CountryOfBirthCode Citizenship
## 1 Associate degree White 0 57 Citizen, Native
## 2 High school Black 0 57 Citizen, Native
## 3 High school Black 0 57 Citizen, Native
## 4 No high school diploma Black 0 57 Citizen, Native
## 5 Associate degree White 0 57 Citizen, Native
## 6 Bachelor's degree White 0 57 Citizen, Native
## EmploymentStatus Industry
## 1 Retired <NA>
## 2 Unemployed Professional and business services
## 3 Disabled <NA>
## 4 Not in Labor Force <NA>
## 5 Employed Professional and business services
## 6 Employed Educational and health services
## PeopleInHousehold Region State MetroAreaCode Age
## 42850 2 Midwest Indiana 26900 73
## 59500 1 Northeast Massachusetts 71650 85
## 84212 3 Northeast New York 35620 51
## 92491 2 Midwest Ohio 18140 25
## 124956 4 West Washington NA 18
## 126712 4 South West Virginia 16620 29
## Married Sex Education Race Hispanic
## 42850 Married Female High school White 0
## 59500 Widowed Female High school White 0
## 84212 Married Male Bachelor's degree White 1
## 92491 Married Female Bachelor's degree White 0
## 124956 Never Married Female High school Black 1
## 126712 Married Male High school White 0
## CountryOfBirthCode Citizenship EmploymentStatus
## 42850 57 Citizen, Native Retired
## 59500 57 Citizen, Native Retired
## 84212 57 Citizen, Native Employed
## 92491 57 Citizen, Native Not in Labor Force
## 124956 57 Citizen, Native Not in Labor Force
## 126712 57 Citizen, Native Employed
## Industry
## 42850 <NA>
## 59500 <NA>
## 84212 Public administration
## 92491 <NA>
## 124956 <NA>
## 126712 Mining
## PeopleInHousehold Region State MetroAreaCode Age Married
## 131294 2 West Wyoming NA 27 Never Married
## 131295 5 West Wyoming NA 39 Divorced
## 131298 5 West Wyoming NA 17 Never Married
## 131299 5 West Wyoming NA 37 Divorced
## 131300 3 West Wyoming NA 58 Married
## 131301 3 West Wyoming NA 53 Married
## Sex Education Race Hispanic CountryOfBirthCode
## 131294 Male High school White 0 57
## 131295 Female Associate degree White 0 57
## 131298 Male No high school diploma White 0 57
## 131299 Male High school White 0 57
## 131300 Male Bachelor's degree White 0 57
## 131301 Female Associate degree White 0 57
## Citizenship EmploymentStatus
## 131294 Citizen, Native Unemployed
## 131295 Citizen, Native Not in Labor Force
## 131298 Citizen, Native Not in Labor Force
## 131299 Citizen, Native Employed
## 131300 Citizen, Native Employed
## 131301 Citizen, Native Not in Labor Force
## Industry
## 131294 Professional and business services
## 131295 <NA>
## 131298 <NA>
## 131299 Mining
## 131300 Financial
## 131301 <NA>
## 'data.frame': 105513 obs. of 14 variables:
## $ PeopleInHousehold : int 1 3 3 3 3 3 3 2 2 2 ...
## $ Region : chr "South" "South" "South" "South" ...
## $ State : chr "Alabama" "Alabama" "Alabama" "Alabama" ...
## $ MetroAreaCode : int 26620 13820 13820 13820 26620 26620 26620 33660 33660 26620 ...
## $ Age : int 85 21 37 18 52 24 26 71 43 52 ...
## $ Married : chr "Widowed" "Never Married" "Never Married" "Never Married" ...
## $ Sex : chr "Female" "Male" "Female" "Male" ...
## $ Education : chr "Associate degree" "High school" "High school" "No high school diploma" ...
## $ Race : chr "White" "Black" "Black" "Black" ...
## $ Hispanic : int 0 0 0 0 0 0 0 0 0 0 ...
## $ CountryOfBirthCode: int 57 57 57 57 57 57 57 57 57 57 ...
## $ Citizenship : chr "Citizen, Native" "Citizen, Native" "Citizen, Native" "Citizen, Native" ...
## $ EmploymentStatus : chr "Retired" "Unemployed" "Disabled" "Not in Labor Force" ...
## $ Industry : chr NA "Professional and business services" NA NA ...## [1] "Creating new feature: Education.fctr..."
## [1] "Creating new feature: Married.fctr..."## Warning in myderiveFeatures(glbObsAll, glbFeatsDerive): arg MetroArea not
## available yet...## [1] "Creating new feature: .pos..."
## [1] "Creating new feature: .pos.y..."## Warning: using .rownames as identifiers for observations## [1] "Partition stats:"## Loading required package: sqldf## Loading required package: gsubfn## Loading required package: proto## Loading required package: RSQLite## Loading required package: DBI## Loading required package: tcltk## EmploymentStatus .src .n
## 1 Employed Train 61733
## 2 <NA> Test 25789
## 3 Retired Train 18619
## 4 Not in Labor Force Train 15246
## 5 Disabled Train 5712
## 6 Unemployed Train 4203
## EmploymentStatus .src .n
## 1 Employed Train 61733
## 2 <NA> Test 25789
## 3 Retired Train 18619
## 4 Not in Labor Force Train 15246
## 5 Disabled Train 5712
## 6 Unemployed Train 4203## Loading required package: RColorBrewer
## .src .n
## 1 Train 105513
## 2 Test 25789## Loading required package: lazyeval## Loading required package: gdata## gdata: read.xls support for 'XLS' (Excel 97-2004) files ENABLED.## ## gdata: read.xls support for 'XLSX' (Excel 2007+) files ENABLED.##
## Attaching package: 'gdata'## The following objects are masked from 'package:dplyr':
##
## combine, first, last## The following object is masked from 'package:stats':
##
## nobs## The following object is masked from 'package:utils':
##
## object.size## [1] "Found 0 duplicates by all features:"## NULL## label step_major step_minor label_minor bgn end elapsed
## 1 import.data 1 0 0 9.784 30.03 20.246
## 2 inspect.data 2 0 0 30.031 NA NAStep 2.0: inspect data
## Warning: Removed 25789 rows containing non-finite values (stat_count).## Loading required package: reshape2
## EmploymentStatus.Disabled EmploymentStatus.Employed
## Test NA NA
## Train 5712 61733
## EmploymentStatus.Not in Labor Force EmploymentStatus.Retired
## Test NA NA
## Train 15246 18619
## EmploymentStatus.Unemployed EmploymentStatus.NA
## Test NA 25789
## Train 4203 NA
## EmploymentStatus.Disabled EmploymentStatus.Employed
## Test NA NA
## Train 0.05413551 0.5850748
## EmploymentStatus.Not in Labor Force EmploymentStatus.Retired
## Test NA NA
## Train 0.144494 0.1764617
## EmploymentStatus.Unemployed EmploymentStatus.NA
## Test NA 1
## Train 0.03983395 NA
## [1] "numeric data missing in glbObsAll: "
## MetroAreaCode
## 34238
## [1] "numeric data w/ 0s in glbObsAll: "
## Age Hispanic
## 1283 113008
## [1] "numeric data w/ Infs in glbObsAll: "
## named integer(0)
## [1] "numeric data w/ NaNs in glbObsAll: "
## named integer(0)
## [1] "string data missing in glbObsAll: "
## Region State Married Sex
## 0 0 NA 0
## Education Race Citizenship EmploymentStatus
## NA 0 0 NA
## Industry
## NA## EmploymentStatus EmploymentStatus.fctr .n
## 1 Employed Employed 61733
## 2 <NA> <NA> 25789
## 3 Retired Retired 18619
## 4 Not in Labor Force Not.in.Labor.Force 15246
## 5 Disabled Disabled 5712
## 6 Unemployed Unemployed 4203## Warning: Removed 1 rows containing missing values (position_stack).
## EmploymentStatus.fctr.Disabled EmploymentStatus.fctr.Employed
## Test NA NA
## Train 5712 61733
## EmploymentStatus.fctr.Not.in.Labor.Force
## Test NA
## Train 15246
## EmploymentStatus.fctr.Retired EmploymentStatus.fctr.Unemployed
## Test NA NA
## Train 18619 4203
## EmploymentStatus.fctr.NA
## Test 25789
## Train NA
## EmploymentStatus.fctr.Disabled EmploymentStatus.fctr.Employed
## Test NA NA
## Train 0.05413551 0.5850748
## EmploymentStatus.fctr.Not.in.Labor.Force
## Test NA
## Train 0.144494
## EmploymentStatus.fctr.Retired EmploymentStatus.fctr.Unemployed
## Test NA NA
## Train 0.1764617 0.03983395
## EmploymentStatus.fctr.NA
## Test 1
## Train NA## Loading required package: caTools
## [1] "elapsed Time (secs): 22.260000"## Scale for 'y' is already present. Adding another scale for 'y', which
## will replace the existing scale.## Scale for 'y' is already present. Adding another scale for 'y', which
## will replace the existing scale.## Warning: Removed 5268 rows containing non-finite values (stat_ydensity).## Warning: Removed 5268 rows containing non-finite values (stat_summary).## Scale for 'y' is already present. Adding another scale for 'y', which
## will replace the existing scale.
## Scale for 'y' is already present. Adding another scale for 'y', which
## will replace the existing scale.
## Scale for 'y' is already present. Adding another scale for 'y', which
## will replace the existing scale.
## Scale for 'y' is already present. Adding another scale for 'y', which
## will replace the existing scale.
## [1] "elapsed Time (secs): 16.943000"
## [1] "elapsed Time (secs): 16.943000"## label step_major step_minor label_minor bgn end elapsed
## 2 inspect.data 2 0 0 30.031 73.211 43.18
## 3 scrub.data 2 1 1 73.211 NA NAStep 2.1: scrub data
## [1] "numeric data missing in glbObsAll: "
## MetroAreaCode EmploymentStatus.fctr
## 34238 25789
## [1] "numeric data w/ 0s in glbObsAll: "
## Age Hispanic
## 1283 113008
## [1] "numeric data w/ Infs in glbObsAll: "
## named integer(0)
## [1] "numeric data w/ NaNs in glbObsAll: "
## named integer(0)
## [1] "string data missing in glbObsAll: "
## Region State Married Sex
## 0 0 NA 0
## Education Race Citizenship EmploymentStatus
## NA 0 0 NA
## Industry
## NA## label step_major step_minor label_minor bgn end elapsed
## 3 scrub.data 2 1 1 73.211 78.514 5.303
## 4 transform.data 2 2 2 78.514 NA NAStep 2.2: transform data
## [1] "Reading file ./data/MetroAreaCodes.csv..."
## [1] "dimensions of data in ./data/MetroAreaCodes.csv: 271 rows x 2 cols"
## Code MetroArea
## 1 460 Appleton-Oshkosh-Neenah, WI
## 2 3000 Grand Rapids-Muskegon-Holland, MI
## 3 3160 Greenville-Spartanburg-Anderson, SC
## 4 3610 Jamestown, NY
## 5 3720 Kalamazoo-Battle Creek, MI
## 6 6450 Portsmouth-Rochester, NH-ME
## Code MetroArea
## 24 12420 Austin-Round Rock, TX
## 52 17140 Cincinnati-Middletown, OH-KY-IN
## 125 29180 Lafayette, LA
## 130 29700 Laredo, TX
## 142 31420 Macon, GA
## 185 39100 Poughkeepsie-Newburgh-Middletown, NY
## Code MetroArea
## 266 76750 Portland-South Portland, ME
## 267 77200 Providence-Fall River-Warwick, MA-RI
## 268 77350 Rochester-Dover, NH-ME
## 269 78100 Springfield, MA-CT
## 270 78700 Waterbury, CT
## 271 79600 Worcester, MA-CT
## 'data.frame': 271 obs. of 2 variables:
## $ Code : int 460 3000 3160 3610 3720 6450 10420 10500 10580 10740 ...
## $ MetroArea: chr "Appleton-Oshkosh-Neenah, WI" "Grand Rapids-Muskegon-Holland, MI" "Greenville-Spartanburg-Anderson, SC" "Jamestown, NY" ...
## - attr(*, "comment")= chr "map_df"
## NULL
## MetroAreaCode MetroArea .n
## 1 NA <NA> 34238
## 2 35620 New York-Northern New Jersey-Long Island, NY-NJ-PA 5409
## 3 47900 Washington-Arlington-Alexandria, DC-VA-MD-WV 4177
## 4 31100 Los Angeles-Long Beach-Santa Ana, CA 4102
## 5 37980 Philadelphia-Camden-Wilmington, PA-NJ-DE 2855
## 6 16980 Chicago-Naperville-Joliet, IN-IN-WI 2772
## MetroAreaCode MetroArea .n
## 36 17460 Cleveland-Elyria-Mentor, OH 681
## 49 31140 Louisville, KY-IN 519
## 81 12940 Baton Rouge, LA 262
## 85 12540 Bakersfield, CA 245
## 100 30460 Lexington-Fayette, KY 198
## 181 43900 Spartanburg, SC 99
## MetroAreaCode MetroArea .n
## 260 46660 Valdosta, GA 42
## 261 47580 Warner Robins, GA 42
## 262 14060 Bloomington-Normal IL 40
## 263 44220 Springfield, OH 34
## 264 36140 Ocean City, NJ 30
## 265 14540 Bowling Green, KY 29## Warning: Removed 1 rows containing missing values (position_stack).
## [1] "Reading file ./data/CountryCodes.csv..."
## [1] "dimensions of data in ./data/CountryCodes.csv: 149 rows x 2 cols"
## Code Country
## 1 57 United States
## 2 66 Guam
## 3 73 Puerto Rico
## 4 78 U. S. Virgin Islands
## 5 96 Other U. S. Island Areas
## 6 100 Albania
## Code Country
## 12 108 Finland
## 24 132 Romania
## 35 149 Slovakia
## 73 231 Pakistan
## 83 247 Vietnam
## 92 313 Guatemala
## Code Country
## 144 508 Fiji
## 145 515 New Zealand
## 146 523 Tonga
## 147 527 Samoa
## 148 528 Oceania, not specified
## 149 555 Elsewhere
## 'data.frame': 149 obs. of 2 variables:
## $ Code : int 57 66 73 78 96 100 102 103 104 105 ...
## $ Country: chr "United States" "Guam" "Puerto Rico" "U. S. Virgin Islands" ...
## - attr(*, "comment")= chr "map_df"
## NULL
## CountryOfBirthCode Country .n
## 1 57 United States 115063
## 2 303 Mexico 3921
## 3 233 Philippines 839
## 4 210 India 770
## 5 207 China 581
## 6 73 Puerto Rico 518
## CountryOfBirthCode Country .n
## 11 301 Canada 410
## 37 440 Nigeria 85
## 94 226 Malaysia 20
## 140 236 Singapore 6
## 143 461 Zimbabwe 6
## 145 527 Samoa 6
## CountryOfBirthCode Country .n
## 156 425 <NA> 3
## 157 142 Northern Ireland 2
## 158 228 <NA> 2
## 159 453 Tanzania 2
## 160 430 <NA> 1
## 161 460 <NA> 1## Warning: Removed 17 rows containing missing values (position_stack).
## Warning in myderiveFeatures(glbObsAll, glbFeatsDerive): Education.fctr
## already present in glbObsAll, skipping ...## Warning in myderiveFeatures(glbObsAll, glbFeatsDerive): Married.fctr
## already present in glbObsAll, skipping ...## [1] "Creating new feature: MetroArea.fctr..."## Warning in myderiveFeatures(glbObsAll, glbFeatsDerive): .pos already
## present in glbObsAll, skipping ...## Warning in myderiveFeatures(glbObsAll, glbFeatsDerive): .pos.y already
## present in glbObsAll, skipping ...## label step_major step_minor label_minor bgn end elapsed
## 4 transform.data 2 2 2 78.514 92.22 13.706
## 5 extract.features 3 0 0 92.220 NA NAStep 3.0: extract features
## label step_major step_minor label_minor bgn
## 5 extract.features 3 0 0 92.220
## 6 extract.features.datetime 3 1 1 98.024
## end elapsed
## 5 98.023 5.804
## 6 NA NAStep 3.1: extract features datetime
## label step_major step_minor label_minor bgn
## 1 extract.features.datetime.bgn 1 0 0 98.051
## end elapsed
## 1 NA NA## label step_major step_minor label_minor bgn
## 6 extract.features.datetime 3 1 1 98.024
## 7 extract.features.image 3 2 2 98.062
## end elapsed
## 6 98.061 0.038
## 7 NA NAStep 3.2: extract features image
```{r extract.features.image, cache=FALSE, echo=FALSE, fig.height=5, fig.width=5, eval=myevlChunk(glbChunks, glbOut$pfx)}
## label step_major step_minor label_minor bgn end
## 1 extract.features.image.bgn 1 0 0 98.096 NA
## elapsed
## 1 NA## label step_major step_minor label_minor bgn
## 1 extract.features.image.bgn 1 0 0 98.096
## 2 extract.features.image.end 2 0 0 98.117
## end elapsed
## 1 98.117 0.021
## 2 NA NA## label step_major step_minor label_minor bgn
## 1 extract.features.image.bgn 1 0 0 98.096
## 2 extract.features.image.end 2 0 0 98.117
## end elapsed
## 1 98.117 0.021
## 2 NA NA## label step_major step_minor label_minor bgn end
## 7 extract.features.image 3 2 2 98.062 98.129
## 8 extract.features.price 3 3 3 98.129 NA
## elapsed
## 7 0.067
## 8 NAStep 3.3: extract features price
## label step_major step_minor label_minor bgn end
## 1 extract.features.price.bgn 1 0 0 98.157 NA
## elapsed
## 1 NA## label step_major step_minor label_minor bgn end
## 8 extract.features.price 3 3 3 98.129 98.167
## 9 extract.features.text 3 4 4 98.168 NA
## elapsed
## 8 0.038
## 9 NAStep 3.4: extract features text
## label step_major step_minor label_minor bgn end
## 1 extract.features.text.bgn 1 0 0 98.21 NA
## elapsed
## 1 NA## label step_major step_minor label_minor bgn end
## 9 extract.features.text 3 4 4 98.168 98.219
## 10 extract.features.string 3 5 5 98.220 NA
## elapsed
## 9 0.052
## 10 NAStep 3.5: extract features string
## label step_major step_minor label_minor bgn end
## 1 extract.features.string.bgn 1 0 0 98.255 NA
## elapsed
## 1 NA## label step_major step_minor
## 1 extract.features.string.bgn 1 0
## 2 extract.features.stringfactorize.str.vars 2 0
## label_minor bgn end elapsed
## 1 0 98.255 98.267 0.012
## 2 0 98.267 NA NA## Region State Married
## "Region" "State" "Married"
## Sex Education Race
## "Sex" "Education" "Race"
## Citizenship EmploymentStatus Industry
## "Citizenship" "EmploymentStatus" "Industry"
## .src MetroArea Country
## ".src" "MetroArea" "Country"## Warning: Creating factors of string variable: Region: # of unique values: 4## Warning: Creating factors of string variable: State: # of unique values: 51## Warning: Creating factors of string variable: Sex: # of unique values: 2## Warning: Creating factors of string variable: Race: # of unique values: 6## Warning: Creating factors of string variable: Citizenship: # of unique
## values: 3## Warning: Creating factors of string variable: Country: # of unique values:
## 145## label step_major step_minor label_minor bgn end
## 10 extract.features.string 3 5 5 98.220 98.567
## 11 extract.features.end 3 6 6 98.568 NA
## elapsed
## 10 0.347
## 11 NAStep 3.6: extract features end
## time trans "bgn " "fit.data.training.all " "predict.data.new " "end "
## 0.0000 multiple enabled transitions: data.training.all data.new model.selected firing: data.training.all
## 1.0000 1 2 1 0 0
## 1.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction firing: data.new
## 2.0000 2 1 1 1 0
## label step_major step_minor label_minor bgn end
## 11 extract.features.end 3 6 6 98.568 99.484
## 12 manage.missing.data 4 0 0 99.484 NA
## elapsed
## 11 0.916
## 12 NAStep 4.0: manage missing data
## [1] "numeric data missing in : "
## MetroAreaCode EmploymentStatus.fctr Country.fctr
## 34238 25789 176
## [1] "numeric data w/ 0s in : "
## Age Hispanic
## 1283 113008
## [1] "numeric data w/ Infs in : "
## named integer(0)
## [1] "numeric data w/ NaNs in : "
## named integer(0)
## [1] "string data missing in : "
## Region State Married Sex
## 0 0 NA 0
## Education Race Citizenship EmploymentStatus
## NA 0 0 NA
## Industry MetroArea Country
## NA NA NA## [1] "numeric data missing in : "
## MetroAreaCode EmploymentStatus.fctr Country.fctr
## 34238 25789 176
## [1] "numeric data w/ 0s in : "
## Age Hispanic
## 1283 113008
## [1] "numeric data w/ Infs in : "
## named integer(0)
## [1] "numeric data w/ NaNs in : "
## named integer(0)
## [1] "string data missing in : "
## Region State Married Sex
## 0 0 NA 0
## Education Race Citizenship EmploymentStatus
## NA 0 0 NA
## Industry MetroArea Country
## NA NA NA## label step_major step_minor label_minor bgn end
## 12 manage.missing.data 4 0 0 99.484 100.641
## 13 cluster.data 5 0 0 100.642 NA
## elapsed
## 12 1.157
## 13 NAStep 5.0: cluster data
## label step_major step_minor label_minor bgn
## 13 cluster.data 5 0 0 100.642
## 14 partition.data.training 6 0 0 101.177
## end elapsed
## 13 101.177 0.535
## 14 NA NAStep 6.0: partition data training
## [1] "partition.data.training chunk: setup: elapsed: 0.00 secs"## [1] "partition.data.training chunk: strata_mtrx complete: elapsed: 0.98 secs"
## [1] "partition.data.training chunk: obs_freq_df complete: elapsed: 0.98 secs"## Loading required package: sampling##
## Attaching package: 'sampling'## The following object is masked from 'package:caret':
##
## cluster## [1] "partition.data.training chunk: Fit/OOB partition complete: elapsed: 3.08 secs"## EmploymentStatus.Disabled EmploymentStatus.Employed
## NA NA
## Fit 4176 45135
## OOB 1536 16598
## EmploymentStatus.Not in Labor Force EmploymentStatus.Retired
## NA NA
## Fit 11147 13613
## OOB 4099 5006
## EmploymentStatus.Unemployed EmploymentStatus.NA
## NA 25789
## Fit 3072 NA
## OOB 1131 NA
## EmploymentStatus.Disabled EmploymentStatus.Employed
## NA NA
## Fit 0.05413323 0.5850822
## OOB 0.05414170 0.5850546
## EmploymentStatus.Not in Labor Force EmploymentStatus.Retired
## NA NA
## Fit 0.1444979 0.1764645
## OOB 0.1444836 0.1764540
## EmploymentStatus.Unemployed EmploymentStatus.NA
## NA 1
## Fit 0.03982215 NA
## OOB 0.03986606 NA
## .category .n.Fit .n.OOB .n.Tst .freqRatio.Fit .freqRatio.OOB
## 1 .dummy 77143 28370 25789 1 1
## .freqRatio.Tst
## 1 1## [1] "glbObsAll: "## [1] 131302 33## [1] "glbObsTrn: "## [1] 105513 33## [1] "glbObsFit: "## [1] 77143 32## [1] "glbObsOOB: "## [1] 28370 32## [1] "glbObsNew: "## [1] 25789 32## [1] "partition.data.training chunk: teardown: elapsed: 6.15 secs"## label step_major step_minor label_minor bgn
## 14 partition.data.training 6 0 0 101.177
## 15 select.features 7 0 0 107.383
## end elapsed
## 14 107.382 6.206
## 15 NA NAStep 7.0: select features
## Warning in cor(data.matrix(entity_df[, sel_feats]), y =
## as.numeric(entity_df[, : the standard deviation is zero## cor.y exclude.as.feat cor.y.abs cor.high.X
## Age 0.2795530159 0 0.2795530159 NA
## Married.fctr 0.1232144895 0 0.1232144895 NA
## Education.fctr 0.0574822155 0 0.0574822155 NA
## Region.fctr 0.0100051406 0 0.0100051406 NA
## MetroArea.fctr 0.0019552594 1 0.0019552594 NA
## Race.fctr -0.0008325811 0 0.0008325811 NA
## .rnorm -0.0027647457 0 0.0027647457 NA
## MetroAreaCode -0.0042435142 1 0.0042435142 NA
## .pos -0.0070536951 1 0.0070536951 NA
## .pos.y -0.0070536951 1 0.0070536951 NA
## .rownames -0.0070989341 1 0.0070989341 NA
## State.fctr -0.0073429705 1 0.0073429705 NA
## Country.fctr -0.0184660650 1 0.0184660650 NA
## Citizenship.fctr -0.0197305604 0 0.0197305604 NA
## Hispanic -0.0202305463 0 0.0202305463 NA
## CountryOfBirthCode -0.0239141640 1 0.0239141640 NA
## Sex.fctr -0.0616145199 0 0.0616145199 NA
## PeopleInHousehold -0.0862747193 0 0.0862747193 NA
## .category NA 1 NA NA
## freqRatio percentUnique zeroVar nzv is.cor.y.abs.low
## Age 1.089125 6.349928e-02 FALSE FALSE FALSE
## Married.fctr 1.797322 4.738753e-03 FALSE FALSE FALSE
## Education.fctr 1.590536 7.582004e-03 FALSE FALSE FALSE
## Region.fctr 1.274445 3.791002e-03 FALSE FALSE FALSE
## MetroArea.fctr 6.253270 2.511539e-01 FALSE FALSE TRUE
## Race.fctr 7.990088 5.686503e-03 FALSE FALSE TRUE
## .rnorm 1.000000 9.964080e+01 FALSE FALSE FALSE
## MetroAreaCode 1.303351 2.502061e-01 FALSE FALSE FALSE
## .pos 1.000000 1.000000e+02 FALSE FALSE FALSE
## .pos.y 1.000000 1.000000e+02 FALSE FALSE FALSE
## .rownames 1.000000 1.000000e+02 FALSE FALSE FALSE
## State.fctr 1.706890 4.833528e-02 FALSE FALSE FALSE
## Country.fctr 24.005593 1.364761e-01 FALSE TRUE FALSE
## Citizenship.fctr 12.901057 2.843252e-03 FALSE FALSE FALSE
## Hispanic 7.182474 1.895501e-03 FALSE FALSE FALSE
## CountryOfBirthCode 24.005593 1.525878e-01 FALSE TRUE FALSE
## Sex.fctr 1.097632 1.895501e-03 FALSE FALSE FALSE
## PeopleInHousehold 1.820761 1.421626e-02 FALSE FALSE FALSE
## .category 0.000000 9.477505e-04 TRUE TRUE NA## Warning in myplot_scatter(plt_feats_df, "percentUnique", "freqRatio",
## colorcol_name = "nzv", : converting nzv to class:factor## Warning: Removed 4 rows containing missing values (geom_point).
## Warning: Removed 4 rows containing missing values (geom_point).
## Warning: Removed 4 rows containing missing values (geom_point).
## cor.y exclude.as.feat cor.y.abs cor.high.X
## Country.fctr -0.01846607 1 0.01846607 NA
## CountryOfBirthCode -0.02391416 1 0.02391416 NA
## .category NA 1 NA NA
## freqRatio percentUnique zeroVar nzv is.cor.y.abs.low
## Country.fctr 24.00559 0.1364760740 FALSE TRUE FALSE
## CountryOfBirthCode 24.00559 0.1525878328 FALSE TRUE FALSE
## .category 0.00000 0.0009477505 TRUE TRUE NA
## [1] "numeric data missing in : "
## MetroAreaCode EmploymentStatus.fctr Country.fctr
## 34238 25789 176
## [1] "numeric data w/ 0s in : "
## Age Hispanic
## 1283 113008
## [1] "numeric data w/ Infs in : "
## named integer(0)
## [1] "numeric data w/ NaNs in : "
## named integer(0)
## [1] "string data missing in : "
## Region State Married Sex
## 0 0 NA 0
## Education Race Citizenship EmploymentStatus
## NA 0 0 NA
## Industry MetroArea Country .lcn
## NA NA NA 25789## [1] "glb_feats_df:"## [1] 19 12## id exclude.as.feat rsp_var
## EmploymentStatus.fctr EmploymentStatus.fctr TRUE TRUE## id cor.y exclude.as.feat
## EmploymentStatus.fctr EmploymentStatus.fctr NA TRUE
## cor.y.abs cor.high.X freqRatio percentUnique zeroVar
## EmploymentStatus.fctr NA NA NA NA NA
## nzv is.cor.y.abs.low interaction.feat
## EmploymentStatus.fctr NA NA NA
## shapiro.test.p.value rsp_var_raw rsp_var
## EmploymentStatus.fctr NA NA TRUE## [1] "glb_feats_df vs. glbObsAll: "## character(0)## [1] "glbObsAll vs. glb_feats_df: "## character(0)## label step_major step_minor label_minor bgn end
## 15 select.features 7 0 0 107.383 118.503
## 16 fit.models 8 0 0 118.503 NA
## elapsed
## 15 11.12
## 16 NAStep 8.0: fit models
fit.models_0_chunk_df <- myadd_chunk(NULL, "fit.models_0_bgn", label.minor = "setup")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_0_bgn 1 0 setup 119.026 NA NA# load(paste0(glbOut$pfx, "dsk.RData"))
get_model_sel_frmla <- function() {
model_evl_terms <- c(NULL)
# min.aic.fit might not be avl
lclMdlEvlCriteria <-
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)]
for (metric in lclMdlEvlCriteria)
model_evl_terms <- c(model_evl_terms,
ifelse(length(grep("max", metric)) > 0, "-", "+"), metric)
if (glb_is_classification && glb_is_binomial)
model_evl_terms <- c(model_evl_terms, "-", "opt.prob.threshold.OOB")
model_sel_frmla <- as.formula(paste(c("~ ", model_evl_terms), collapse = " "))
return(model_sel_frmla)
}
get_dsp_models_df <- function() {
dsp_models_cols <- c("id",
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)],
grep("opt.", names(glb_models_df), fixed = TRUE, value = TRUE))
dsp_models_df <-
#orderBy(get_model_sel_frmla(), glb_models_df)[, c("id", glbMdlMetricsEval)]
orderBy(get_model_sel_frmla(), glb_models_df)[, dsp_models_cols]
nCvMdl <- sapply(glb_models_lst, function(mdl) nrow(mdl$results))
nParams <- sapply(glb_models_lst, function(mdl) ifelse(mdl$method == "custom", 0,
nrow(subset(modelLookup(mdl$method), parameter != "parameter"))))
# nCvMdl <- nCvMdl[names(nCvMdl) != "avNNet"]
# nParams <- nParams[names(nParams) != "avNNet"]
if (length(cvMdlProblems <- nCvMdl[nCvMdl <= nParams]) > 0) {
print("Cross Validation issues:")
warning("Cross Validation issues:")
print(cvMdlProblems)
}
pltMdls <- setdiff(names(nCvMdl), names(cvMdlProblems))
pltMdls <- setdiff(pltMdls, names(nParams[nParams == 0]))
# length(pltMdls) == 21
png(paste0(glbOut$pfx, "bestTune.png"), width = 480 * 2, height = 480 * 4)
grid.newpage()
pushViewport(viewport(layout = grid.layout(ceiling(length(pltMdls) / 2.0), 2)))
pltIx <- 1
for (mdlId in pltMdls) {
print(ggplot(glb_models_lst[[mdlId]], highBestTune = TRUE) + labs(title = mdlId),
vp = viewport(layout.pos.row = ceiling(pltIx / 2.0),
layout.pos.col = ((pltIx - 1) %% 2) + 1))
pltIx <- pltIx + 1
}
dev.off()
if (all(row.names(dsp_models_df) != dsp_models_df$id))
row.names(dsp_models_df) <- dsp_models_df$id
return(dsp_models_df)
}
#get_dsp_models_df()
if (glb_is_classification && glb_is_binomial &&
(length(unique(glbObsFit[, glb_rsp_var])) < 2))
stop("glbObsFit$", glb_rsp_var, ": contains less than 2 unique values: ",
paste0(unique(glbObsFit[, glb_rsp_var]), collapse=", "))
max_cor_y_x_vars <- orderBy(~ -cor.y.abs,
subset(glb_feats_df, (exclude.as.feat == 0) & !nzv & !is.cor.y.abs.low &
is.na(cor.high.X)))[1:2, "id"]
max_cor_y_x_vars <- max_cor_y_x_vars[!is.na(max_cor_y_x_vars)]
if (length(max_cor_y_x_vars) < 2)
max_cor_y_x_vars <- union(max_cor_y_x_vars, ".pos")
if (!is.null(glb_Baseline_mdl_var)) {
if ((max_cor_y_x_vars[1] != glb_Baseline_mdl_var) &
(glb_feats_df[glb_feats_df$id == max_cor_y_x_vars[1], "cor.y.abs"] >
glb_feats_df[glb_feats_df$id == glb_Baseline_mdl_var, "cor.y.abs"]))
stop(max_cor_y_x_vars[1], " has a higher correlation with ", glb_rsp_var,
" than the Baseline var: ", glb_Baseline_mdl_var)
}
glb_model_type <- ifelse(glb_is_regression, "regression", "classification")
# Model specs
# c("id.prefix", "method", "type",
# # trainControl params
# "preProc.method", "cv.n.folds", "cv.n.repeats", "summary.fn",
# # train params
# "metric", "metric.maximize", "tune.df")
# Baseline
if (!is.null(glb_Baseline_mdl_var)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Baseline"), major.inc = FALSE,
label.minor = "mybaseln_classfr")
ret_lst <- myfit_mdl(mdl_id="Baseline",
model_method="mybaseln_classfr",
indepVar=glb_Baseline_mdl_var,
rsp_var=glb_rsp_var,
fit_df=glbObsFit, OOB_df=glbObsOOB)
}
# Most Frequent Outcome "MFO" model: mean(y) for regression
# Not using caret's nullModel since model stats not avl
# Cannot use rpart for multinomial classification since it predicts non-MFO
if (glb_is_classification) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "MFO"), major.inc = FALSE,
label.minor = "myMFO_classfr")
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "MFO", type = glb_model_type, trainControl.method = "none",
train.method = ifelse(glb_is_regression, "lm", "myMFO_classfr"))),
indepVar = ".rnorm", rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
# "random" model - only for classification;
# none needed for regression since it is same as MFO
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Random"), major.inc = FALSE,
label.minor = "myrandom_classfr")
#stop(here"); glb2Sav(); all.equal(glb_models_df, sav_models_df)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Random", type = glb_model_type, trainControl.method = "none",
train.method = "myrandom_classfr")),
indepVar = ".rnorm", rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}## label step_major step_minor label_minor bgn end
## 1 fit.models_0_bgn 1 0 setup 119.026 119.059
## 2 fit.models_0_MFO 1 1 myMFO_classfr 119.059 NA
## elapsed
## 1 0.033
## 2 NA
## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: MFO###myMFO_classfr"
## [1] " indepVar: .rnorm"
## [1] "myfit_mdl: setup complete: 0.421000 secs"
## Fitting parameter = none on full training set
## [1] "in MFO.Classifier$fit"
## [1] "unique.vals:"
## [1] Disabled Employed Not.in.Labor.Force
## [4] Retired Unemployed
## Levels: Disabled Employed Not.in.Labor.Force Retired Unemployed
## [1] "unique.prob:"
## y
## Employed Retired Not.in.Labor.Force
## 0.58508225 0.17646449 0.14449788
## Disabled Unemployed
## 0.05413323 0.03982215
## [1] "MFO.val:"
## [1] "Employed"
## [1] "myfit_mdl: train complete: 0.995000 secs"
## Length Class Mode
## unique.vals 5 factor numeric
## unique.prob 5 -none- numeric
## MFO.val 1 -none- character
## x.names 1 -none- character
## xNames 1 -none- character
## problemType 1 -none- character
## tuneValue 1 data.frame list
## obsLevels 5 -none- character
## [1] "myfit_mdl: train diagnostics complete: 0.997000 secs"
## [1] "entr MFO.Classifier$predict"
## [1] "exit MFO.Classifier$predict"
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 0 4176 0 0
## Employed 0 45135 0 0
## Not.in.Labor.Force 0 11147 0 0
## Retired 0 13613 0 0
## Unemployed 0 3072 0 0
## Prediction
## Reference Unemployed
## Disabled 0
## Employed 0
## Not.in.Labor.Force 0
## Retired 0
## Unemployed 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.5850822 0.0000000 0.5815957 0.5885624 0.5850822
## AccuracyPValue McnemarPValue
## 0.5015403 NaN
## [1] "entr MFO.Classifier$predict"
## [1] "exit MFO.Classifier$predict"
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 0 1536 0 0
## Employed 0 16598 0 0
## Not.in.Labor.Force 0 4099 0 0
## Retired 0 5006 0 0
## Unemployed 0 1131 0 0
## Prediction
## Reference Unemployed
## Disabled 0
## Employed 0
## Not.in.Labor.Force 0
## Retired 0
## Unemployed 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.5850546 0.0000000 0.5792951 0.5907967 0.5850546
## AccuracyPValue McnemarPValue
## 0.5025398 NaN
## [1] "myfit_mdl: predict complete: 1.288000 secs"
## id feats max.nTuningRuns min.elapsedtime.everything
## 1 MFO###myMFO_classfr .rnorm 0 0.484
## min.elapsedtime.final max.Accuracy.fit max.AccuracyLower.fit
## 1 0.02 0.5850822 0.5815957
## max.AccuracyUpper.fit max.Kappa.fit max.Accuracy.OOB
## 1 0.5885624 0 0.5850546
## max.AccuracyLower.OOB max.AccuracyUpper.OOB max.Kappa.OOB
## 1 0.5792951 0.5907967 0
## [1] "myfit_mdl: exit: 1.293000 secs"
## label step_major step_minor label_minor bgn
## 2 fit.models_0_MFO 1 1 myMFO_classfr 119.059
## 3 fit.models_0_Random 1 2 myrandom_classfr 120.358
## end elapsed
## 2 120.358 1.299
## 3 NA NA
## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Random###myrandom_classfr"
## [1] " indepVar: .rnorm"
## [1] "myfit_mdl: setup complete: 0.417000 secs"
## Fitting parameter = none on full training set
## [1] "myfit_mdl: train complete: 0.832000 secs"
## Length Class Mode
## unique.vals 5 factor numeric
## unique.prob 5 table numeric
## xNames 1 -none- character
## problemType 1 -none- character
## tuneValue 1 data.frame list
## obsLevels 5 -none- character
## [1] "myfit_mdl: train diagnostics complete: 0.833000 secs"
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 239 2488 605 677
## Employed 2500 26395 6634 7851
## Not.in.Labor.Force 566 6529 1646 1988
## Retired 734 7958 1929 2431
## Unemployed 171 1732 475 574
## Prediction
## Reference Unemployed
## Disabled 167
## Employed 1755
## Not.in.Labor.Force 418
## Retired 561
## Unemployed 120
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.399660371 0.001664263 0.396201158 0.403127131 0.585082250
## AccuracyPValue McnemarPValue
## 1.000000000 0.434626705
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 83 896 219 276
## Employed 922 9745 2383 2890
## Not.in.Labor.Force 228 2400 584 753
## Retired 272 2914 777 865
## Unemployed 54 630 159 241
## Prediction
## Reference Unemployed
## Disabled 62
## Employed 658
## Not.in.Labor.Force 134
## Retired 178
## Unemployed 47
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.3991540360 0.0006568311 0.3934483537 0.4048803781 0.5850546352
## AccuracyPValue McnemarPValue
## 1.0000000000 0.1783274495
## [1] "myfit_mdl: predict complete: 1.115000 secs"
## id feats max.nTuningRuns
## 1 Random###myrandom_classfr .rnorm 0
## min.elapsedtime.everything min.elapsedtime.final max.Accuracy.fit
## 1 0.336 0.017 0.3996604
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.3962012 0.4031271 0.001664263
## max.Accuracy.OOB max.AccuracyLower.OOB max.AccuracyUpper.OOB
## 1 0.399154 0.3934484 0.4048804
## max.Kappa.OOB
## 1 0.0006568311
## [1] "myfit_mdl: exit: 1.121000 secs"# Max.cor.Y
# Check impact of cv
# rpart is not a good candidate since caret does not optimize cp (only tuning parameter of rpart) well
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.rcv.*X*"), major.inc = FALSE,
label.minor = "glmnet")## label step_major step_minor label_minor
## 3 fit.models_0_Random 1 2 myrandom_classfr
## 4 fit.models_0_Max.cor.Y.rcv.*X* 1 3 glmnet
## bgn end elapsed
## 3 120.358 121.487 1.13
## 4 121.488 NA NAret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.rcv.1X1", type = glb_model_type, trainControl.method = "none",
train.method = "glmnet")),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Max.cor.Y.rcv.1X1###glmnet"
## [1] " indepVar: Age,Married.fctr"
## [1] "myfit_mdl: setup complete: 0.689000 secs"## Loading required package: glmnet## Loading required package: Matrix## Loaded glmnet 2.0-5## Fitting alpha = 0.1, lambda = 0.0047 on full training set
## [1] "myfit_mdl: train complete: 12.953000 secs"
## Length Class Mode
## a0 470 -none- numeric
## beta 5 -none- list
## dfmat 470 -none- numeric
## df 94 -none- numeric
## dim 2 -none- numeric
## lambda 94 -none- numeric
## dev.ratio 94 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 5 -none- character
## grouped 1 -none- logical
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 6 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 5 -none- character
## [1] "min lambda > lambdaOpt:"
## [1] "class: Disabled:"
## Age Married.fctrMarried
## -0.79408299 0.01681048 -0.75127170
## Married.fctrSeparated
## 0.30130582
## [1] "class: Employed:"
## Age
## 3.32044469 -0.02694435
## Married.fctrMarried Married.fctrNever Married
## 0.18106620 -0.28269559
## Married.fctrSeparated Married.fctrWidowed
## -0.10075966 -0.46256333
## [1] "class: Not.in.Labor.Force:"
## Age
## 3.45602240 -0.07655272
## Married.fctrMarried Married.fctrNever Married
## 0.29037877 0.24408828
## Married.fctrWidowed
## 0.38951353
## [1] "class: Retired:"
## Age
## -6.6894460 0.1207445
## Married.fctrMarried Married.fctrNever Married
## 0.3430942 -0.2086412
## Married.fctrSeparated Married.fctrWidowed
## -0.3020523 0.4416997
## [1] "class: Unemployed:"
## Age
## 0.70706190 -0.02811681
## Married.fctrMarried Married.fctrNever Married
## -0.28571885 0.20779628
## Married.fctrSeparated Married.fctrWidowed
## 0.17756720 -0.25509042
## [1] "max lambda < lambdaOpt:"
## [1] "class: Disabled:"
## Age Married.fctrMarried
## -0.79155512 0.01703241 -0.76152146
## Married.fctrSeparated
## 0.29311512
## [1] "class: Employed:"
## Age
## 3.34448750 -0.02725668
## Married.fctrMarried Married.fctrNever Married
## 0.18152622 -0.28275686
## Married.fctrSeparated Married.fctrWidowed
## -0.10828143 -0.45559728
## [1] "class: Not.in.Labor.Force:"
## Age
## 3.49941749 -0.07762232
## Married.fctrMarried Married.fctrNever Married
## 0.30261115 0.24431988
## Married.fctrWidowed
## 0.42244384
## [1] "class: Retired:"
## Age
## -6.8056729 0.1226320
## Married.fctrMarried Married.fctrNever Married
## 0.3459936 -0.2062815
## Married.fctrSeparated Married.fctrWidowed
## -0.3104299 0.4389381
## [1] "class: Unemployed:"
## Age
## 0.75332300 -0.02884429
## Married.fctrMarried Married.fctrNever Married
## -0.29106089 0.20042477
## Married.fctrSeparated Married.fctrWidowed
## 0.17345975 -0.25949726
## [1] "myfit_mdl: train diagnostics complete: 13.333000 secs"
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 0 3663 0 513
## Employed 0 43079 3 2053
## Not.in.Labor.Force 0 10891 4 252
## Retired 0 3911 0 9702
## Unemployed 0 2970 0 102
## Prediction
## Reference Unemployed
## Disabled 0
## Employed 0
## Not.in.Labor.Force 0
## Retired 0
## Unemployed 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.6842487 0.3446629 0.6809553 0.6875283 0.5850822
## AccuracyPValue McnemarPValue
## 0.0000000 NaN
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 0 1362 0 174
## Employed 0 15859 1 738
## Not.in.Labor.Force 0 4003 1 95
## Retired 0 1404 1 3601
## Unemployed 0 1105 0 26
## Prediction
## Reference Unemployed
## Disabled 0
## Employed 0
## Not.in.Labor.Force 0
## Retired 0
## Unemployed 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 6.859711e-01 3.481272e-01 6.805339e-01 6.913702e-01 5.850546e-01
## AccuracyPValue McnemarPValue
## 2.504519e-269 NaN
## [1] "myfit_mdl: predict complete: 14.592000 secs"
## id feats max.nTuningRuns
## 1 Max.cor.Y.rcv.1X1###glmnet Age,Married.fctr 0
## min.elapsedtime.everything min.elapsedtime.final max.Accuracy.fit
## 1 12.169 10.348 0.6842487
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.6809553 0.6875283 0.3446629
## max.Accuracy.OOB max.AccuracyLower.OOB max.AccuracyUpper.OOB
## 1 0.6859711 0.6805339 0.6913702
## max.Kappa.OOB
## 1 0.3481272
## [1] "myfit_mdl: exit: 14.598000 secs"if (glbMdlCheckRcv) {
# rcv_n_folds == 1 & rcv_n_repeats > 1 crashes
for (rcv_n_folds in seq(3, glb_rcv_n_folds + 2, 2))
for (rcv_n_repeats in seq(1, glb_rcv_n_repeats + 2, 2)) {
# Experiment specific code to avoid caret crash
# lcl_tune_models_df <- rbind(data.frame()
# ,data.frame(method = "glmnet", parameter = "alpha",
# vals = "0.100 0.325 0.550 0.775 1.000")
# ,data.frame(method = "glmnet", parameter = "lambda",
# vals = "9.342e-02")
# )
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst =
list(
id.prefix = paste0("Max.cor.Y.rcv.", rcv_n_folds, "X", rcv_n_repeats),
type = glb_model_type,
# tune.df = lcl_tune_models_df,
trainControl.method = "repeatedcv",
trainControl.number = rcv_n_folds,
trainControl.repeats = rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.method = "glmnet", train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize)),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
# Add parallel coordinates graph of glb_models_df[, glbMdlMetricsEval] to evaluate cv parameters
tmp_models_cols <- c("id", "max.nTuningRuns",
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)],
grep("opt.", names(glb_models_df), fixed = TRUE, value = TRUE))
print(myplot_parcoord(obs_df = subset(glb_models_df,
grepl("Max.cor.Y.rcv.", id, fixed = TRUE),
select = -feats)[, tmp_models_cols],
id_var = "id"))
}
# Useful for stacking decisions
# fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
# paste0("fit.models_0_", "Max.cor.Y[rcv.1X1.cp.0|]"), major.inc = FALSE,
# label.minor = "rpart")
#
# ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
# id.prefix = "Max.cor.Y.rcv.1X1.cp.0", type = glb_model_type, trainControl.method = "none",
# train.method = "rpart",
# tune.df=data.frame(method="rpart", parameter="cp", min=0.0, max=0.0, by=0.1))),
# indepVar=max_cor_y_x_vars, rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB)
#stop(here"); glb2Sav(); all.equal(glb_models_df, sav_models_df)
# if (glb_is_regression || glb_is_binomial) # For multinomials this model will be run next by default
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y",
type = glb_model_type, trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "rpart")),
indepVar = max_cor_y_x_vars, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Max.cor.Y##rcv#rpart"
## [1] " indepVar: Age,Married.fctr"
## [1] "myfit_mdl: setup complete: 0.691000 secs"## Loading required package: rpart## + Fold1.Rep1: cp=0.0001406
## - Fold1.Rep1: cp=0.0001406
## + Fold2.Rep1: cp=0.0001406
## - Fold2.Rep1: cp=0.0001406
## + Fold3.Rep1: cp=0.0001406
## - Fold3.Rep1: cp=0.0001406
## + Fold1.Rep2: cp=0.0001406
## - Fold1.Rep2: cp=0.0001406
## + Fold2.Rep2: cp=0.0001406
## - Fold2.Rep2: cp=0.0001406
## + Fold3.Rep2: cp=0.0001406
## - Fold3.Rep2: cp=0.0001406
## + Fold1.Rep3: cp=0.0001406
## - Fold1.Rep3: cp=0.0001406
## + Fold2.Rep3: cp=0.0001406
## - Fold2.Rep3: cp=0.0001406
## + Fold3.Rep3: cp=0.0001406
## - Fold3.Rep3: cp=0.0001406
## Aggregating results
## Selecting tuning parameters
## Fitting cp = 0.000141 on full training set
## [1] "myfit_mdl: train complete: 15.491000 secs"## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = "Max.cor.Y", : model's bestTune found at an extreme of
## tuneGrid for parameter: cp## Loading required package: rpart.plot
## Call:
## rpart(formula = .outcome ~ ., control = list(minsplit = 20, minbucket = 7,
## cp = 0, maxcompete = 4, maxsurrogate = 5, usesurrogate = 2,
## surrogatestyle = 0, maxdepth = 30, xval = 0))
## n= 77143
##
## CP nsplit rel error
## 1 0.2493439140 0 1.0000000
## 2 0.0896338415 1 0.7506561
## 3 0.0007185704 2 0.6610222
## 4 0.0002999250 4 0.6595851
## 5 0.0001405899 10 0.6577106
##
## Variable importance
## Age Married.fctrWidowed
## 89 11
##
## Node number 1: 77143 observations, complexity param=0.2493439
## predicted class=Employed expected loss=0.4149178 P(node) =1
## class counts: 4176 45135 11147 13613 3072
## probabilities: 0.054 0.585 0.144 0.176 0.040
## left son=2 (61353 obs) right son=3 (15790 obs)
## Primary splits:
## Age < 63.5 to the left, improve=8858.26400, (0 missing)
## Married.fctrWidowed < 0.5 to the left, improve=2212.80200, (0 missing)
## Married.fctrNever Married < 0.5 to the right, improve=1406.87800, (0 missing)
## Married.fctrMarried < 0.5 to the right, improve= 568.87570, (0 missing)
## Married.fctrSeparated < 0.5 to the right, improve= 27.73184, (0 missing)
## Surrogate splits:
## Married.fctrWidowed < 0.5 to the left, agree=0.831, adj=0.173, (0 split)
##
## Node number 2: 61353 observations, complexity param=0.08963384
## predicted class=Employed expected loss=0.3178003 P(node) =0.7953152
## class counts: 3455 41855 10786 2352 2905
## probabilities: 0.056 0.682 0.176 0.038 0.047
## left son=4 (55227 obs) right son=5 (6126 obs)
## Primary splits:
## Age < 19.5 to the right, improve=3276.07000, (0 missing)
## Married.fctrNever Married < 0.5 to the left, improve=1005.29500, (0 missing)
## Married.fctrMarried < 0.5 to the right, improve= 661.88050, (0 missing)
## Married.fctrWidowed < 0.5 to the left, improve= 75.61422, (0 missing)
## Married.fctrSeparated < 0.5 to the right, improve= 11.33257, (0 missing)
##
## Node number 3: 15790 observations, complexity param=0.000299925
## predicted class=Retired expected loss=0.2868271 P(node) =0.2046848
## class counts: 721 3280 361 11261 167
## probabilities: 0.046 0.208 0.023 0.713 0.011
## left son=6 (6763 obs) right son=7 (9027 obs)
## Primary splits:
## Age < 70.5 to the left, improve=476.176400, (0 missing)
## Married.fctrWidowed < 0.5 to the left, improve=121.490300, (0 missing)
## Married.fctrMarried < 0.5 to the right, improve= 28.613000, (0 missing)
## Married.fctrNever Married < 0.5 to the right, improve= 12.000990, (0 missing)
## Married.fctrSeparated < 0.5 to the right, improve= 7.042472, (0 missing)
## Surrogate splits:
## Married.fctrNever Married < 0.5 to the right, agree=0.576, adj=0.010, (0 split)
## Married.fctrWidowed < 0.5 to the left, agree=0.575, adj=0.008, (0 split)
## Married.fctrSeparated < 0.5 to the right, agree=0.572, adj=0.000, (0 split)
##
## Node number 4: 55227 observations
## predicted class=Employed expected loss=0.2679124 P(node) =0.7159042
## class counts: 3386 40431 6493 2348 2569
## probabilities: 0.061 0.732 0.118 0.043 0.047
##
## Node number 5: 6126 observations, complexity param=0.0007185704
## predicted class=Not.in.Labor.Force expected loss=0.2992165 P(node) =0.07941096
## class counts: 69 1424 4293 4 336
## probabilities: 0.011 0.232 0.701 0.001 0.055
## left son=10 (2249 obs) right son=11 (3877 obs)
## Primary splits:
## Age < 17.5 to the right, improve=240.7698000, (0 missing)
## Married.fctrNever Married < 0.5 to the left, improve= 4.2843080, (0 missing)
## Married.fctrMarried < 0.5 to the right, improve= 3.8272960, (0 missing)
## Married.fctrSeparated < 0.5 to the left, improve= 0.3026384, (0 missing)
## Surrogate splits:
## Married.fctrMarried < 0.5 to the right, agree=0.635, adj=0.007, (0 split)
##
## Node number 6: 6763 observations, complexity param=0.000299925
## predicted class=Retired expected loss=0.4422594 P(node) =0.08766836
## class counts: 421 2253 200 3772 117
## probabilities: 0.062 0.333 0.030 0.558 0.017
## left son=12 (2239 obs) right son=13 (4524 obs)
## Primary splits:
## Age < 65.5 to the left, improve=57.801150, (0 missing)
## Married.fctrMarried < 0.5 to the left, improve=15.646450, (0 missing)
## Married.fctrWidowed < 0.5 to the left, improve= 8.354322, (0 missing)
## Married.fctrSeparated < 0.5 to the right, improve= 4.612768, (0 missing)
## Married.fctrNever Married < 0.5 to the right, improve= 3.596623, (0 missing)
##
## Node number 7: 9027 observations
## predicted class=Retired expected loss=0.1703778 P(node) =0.1170164
## class counts: 300 1027 161 7489 50
## probabilities: 0.033 0.114 0.018 0.830 0.006
##
## Node number 10: 2249 observations, complexity param=0.0007185704
## predicted class=Not.in.Labor.Force expected loss=0.4988884 P(node) =0.02915365
## class counts: 28 890 1127 2 202
## probabilities: 0.012 0.396 0.501 0.001 0.090
## left son=20 (1106 obs) right son=21 (1143 obs)
## Primary splits:
## Age < 18.5 to the right, improve=23.60859000, (0 missing)
## Married.fctrNever Married < 0.5 to the left, improve= 2.01601700, (0 missing)
## Married.fctrMarried < 0.5 to the right, improve= 0.75289140, (0 missing)
## Married.fctrSeparated < 0.5 to the left, improve= 0.09759261, (0 missing)
## Surrogate splits:
## Married.fctrNever Married < 0.5 to the left, agree=0.517, adj=0.017, (0 split)
## Married.fctrMarried < 0.5 to the right, agree=0.515, adj=0.014, (0 split)
## Married.fctrSeparated < 0.5 to the right, agree=0.509, adj=0.002, (0 split)
##
## Node number 11: 3877 observations
## predicted class=Not.in.Labor.Force expected loss=0.1833892 P(node) =0.05025731
## class counts: 41 534 3166 2 134
## probabilities: 0.011 0.138 0.817 0.001 0.035
##
## Node number 12: 2239 observations, complexity param=0.000299925
## predicted class=Retired expected loss=0.5475659 P(node) =0.02902402
## class counts: 190 914 77 1013 45
## probabilities: 0.085 0.408 0.034 0.452 0.020
## left son=24 (730 obs) right son=25 (1509 obs)
## Primary splits:
## Married.fctrMarried < 0.5 to the left, improve=9.408466, (0 missing)
## Age < 64.5 to the left, improve=8.638895, (0 missing)
## Married.fctrSeparated < 0.5 to the right, improve=3.217616, (0 missing)
## Married.fctrNever Married < 0.5 to the right, improve=1.756960, (0 missing)
## Married.fctrWidowed < 0.5 to the left, improve=1.238922, (0 missing)
## Surrogate splits:
## Married.fctrWidowed < 0.5 to the right, agree=0.753, adj=0.242, (0 split)
## Married.fctrNever Married < 0.5 to the right, agree=0.741, adj=0.205, (0 split)
## Married.fctrSeparated < 0.5 to the right, agree=0.686, adj=0.037, (0 split)
##
## Node number 13: 4524 observations
## predicted class=Retired expected loss=0.3901415 P(node) =0.05864434
## class counts: 231 1339 123 2759 72
## probabilities: 0.051 0.296 0.027 0.610 0.016
##
## Node number 20: 1106 observations
## predicted class=Employed expected loss=0.534358 P(node) =0.01433701
## class counts: 16 515 469 2 104
## probabilities: 0.014 0.466 0.424 0.002 0.094
##
## Node number 21: 1143 observations
## predicted class=Not.in.Labor.Force expected loss=0.424322 P(node) =0.01481664
## class counts: 12 375 658 0 98
## probabilities: 0.010 0.328 0.576 0.000 0.086
##
## Node number 24: 730 observations, complexity param=0.000299925
## predicted class=Employed expected loss=0.6068493 P(node) =0.009462945
## class counts: 110 287 27 284 22
## probabilities: 0.151 0.393 0.037 0.389 0.030
## left son=48 (553 obs) right son=49 (177 obs)
## Primary splits:
## Married.fctrWidowed < 0.5 to the left, improve=3.8573460, (0 missing)
## Married.fctrSeparated < 0.5 to the right, improve=1.8347000, (0 missing)
## Age < 64.5 to the left, improve=1.8184380, (0 missing)
## Married.fctrNever Married < 0.5 to the left, improve=0.7679924, (0 missing)
##
## Node number 25: 1509 observations, complexity param=0.000299925
## predicted class=Retired expected loss=0.5168986 P(node) =0.01956107
## class counts: 80 627 50 729 23
## probabilities: 0.053 0.416 0.033 0.483 0.015
## left son=50 (755 obs) right son=51 (754 obs)
## Primary splits:
## Age < 64.5 to the left, improve=7.060871, (0 missing)
##
## Node number 48: 553 observations, complexity param=0.000299925
## predicted class=Employed expected loss=0.5949367 P(node) =0.007168505
## class counts: 90 224 24 195 20
## probabilities: 0.163 0.405 0.043 0.353 0.036
## left son=96 (403 obs) right son=97 (150 obs)
## Primary splits:
## Married.fctrNever Married < 0.5 to the left, improve=1.8459710, (0 missing)
## Married.fctrSeparated < 0.5 to the right, improve=1.3472590, (0 missing)
## Age < 64.5 to the left, improve=0.5622227, (0 missing)
##
## Node number 49: 177 observations
## predicted class=Retired expected loss=0.4971751 P(node) =0.00229444
## class counts: 20 63 3 89 2
## probabilities: 0.113 0.356 0.017 0.503 0.011
##
## Node number 50: 755 observations
## predicted class=Employed expected loss=0.5470199 P(node) =0.009787019
## class counts: 39 342 35 323 16
## probabilities: 0.052 0.453 0.046 0.428 0.021
##
## Node number 51: 754 observations
## predicted class=Retired expected loss=0.4615385 P(node) =0.009774056
## class counts: 41 285 15 406 7
## probabilities: 0.054 0.378 0.020 0.538 0.009
##
## Node number 96: 403 observations
## predicted class=Employed expected loss=0.5707196 P(node) =0.005224064
## class counts: 67 173 16 132 15
## probabilities: 0.166 0.429 0.040 0.328 0.037
##
## Node number 97: 150 observations
## predicted class=Retired expected loss=0.58 P(node) =0.001944441
## class counts: 23 51 8 63 5
## probabilities: 0.153 0.340 0.053 0.420 0.033
##
## n= 77143
##
## node), split, n, loss, yval, (yprob)
## * denotes terminal node
##
## 1) root 77143 32008 Employed (0.054 0.59 0.14 0.18 0.04)
## 2) Age< 63.5 61353 19498 Employed (0.056 0.68 0.18 0.038 0.047)
## 4) Age>=19.5 55227 14796 Employed (0.061 0.73 0.12 0.043 0.047) *
## 5) Age< 19.5 6126 1833 Not.in.Labor.Force (0.011 0.23 0.7 0.00065 0.055)
## 10) Age>=17.5 2249 1122 Not.in.Labor.Force (0.012 0.4 0.5 0.00089 0.09)
## 20) Age>=18.5 1106 591 Employed (0.014 0.47 0.42 0.0018 0.094) *
## 21) Age< 18.5 1143 485 Not.in.Labor.Force (0.01 0.33 0.58 0 0.086) *
## 11) Age< 17.5 3877 711 Not.in.Labor.Force (0.011 0.14 0.82 0.00052 0.035) *
## 3) Age>=63.5 15790 4529 Retired (0.046 0.21 0.023 0.71 0.011)
## 6) Age< 70.5 6763 2991 Retired (0.062 0.33 0.03 0.56 0.017)
## 12) Age< 65.5 2239 1226 Retired (0.085 0.41 0.034 0.45 0.02)
## 24) Married.fctrMarried< 0.5 730 443 Employed (0.15 0.39 0.037 0.39 0.03)
## 48) Married.fctrWidowed< 0.5 553 329 Employed (0.16 0.41 0.043 0.35 0.036)
## 96) Married.fctrNever Married< 0.5 403 230 Employed (0.17 0.43 0.04 0.33 0.037) *
## 97) Married.fctrNever Married>=0.5 150 87 Retired (0.15 0.34 0.053 0.42 0.033) *
## 49) Married.fctrWidowed>=0.5 177 88 Retired (0.11 0.36 0.017 0.5 0.011) *
## 25) Married.fctrMarried>=0.5 1509 780 Retired (0.053 0.42 0.033 0.48 0.015)
## 50) Age< 64.5 755 413 Employed (0.052 0.45 0.046 0.43 0.021) *
## 51) Age>=64.5 754 348 Retired (0.054 0.38 0.02 0.54 0.0093) *
## 13) Age>=65.5 4524 1765 Retired (0.051 0.3 0.027 0.61 0.016) *
## 7) Age>=70.5 9027 1538 Retired (0.033 0.11 0.018 0.83 0.0055) *
## [1] "myfit_mdl: train diagnostics complete: 16.344000 secs"
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 0 3508 53 615
## Employed 0 41461 909 2765
## Not.in.Labor.Force 0 7013 3824 310
## Retired 0 2805 2 10806
## Unemployed 0 2704 232 136
## Prediction
## Reference Unemployed
## Disabled 0
## Employed 0
## Not.in.Labor.Force 0
## Retired 0
## Unemployed 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.7271042 0.4763005 0.7239458 0.7302455 0.5850822
## AccuracyPValue McnemarPValue
## 0.0000000 NaN
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 0 1280 28 228
## Employed 0 15235 358 1005
## Not.in.Labor.Force 0 2578 1399 122
## Retired 0 995 1 4010
## Unemployed 0 993 98 40
## Prediction
## Reference Unemployed
## Disabled 0
## Employed 0
## Not.in.Labor.Force 0
## Retired 0
## Unemployed 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.7276701 0.4783439 0.7224493 0.7328442 0.5850546
## AccuracyPValue McnemarPValue
## 0.0000000 NaN
## [1] "myfit_mdl: predict complete: 16.773000 secs"
## id feats max.nTuningRuns
## 1 Max.cor.Y##rcv#rpart Age,Married.fctr 5
## min.elapsedtime.everything min.elapsedtime.final max.Accuracy.fit
## 1 14.705 0.399 0.7264431
## max.AccuracyLower.fit max.AccuracyUpper.fit max.Kappa.fit
## 1 0.7239458 0.7302455 0.4771251
## max.Accuracy.OOB max.AccuracyLower.OOB max.AccuracyUpper.OOB
## 1 0.7276701 0.7224493 0.7328442
## max.Kappa.OOB max.AccuracySD.fit max.KappaSD.fit
## 1 0.4783439 0.002327336 0.005671842
## [1] "myfit_mdl: exit: 16.783000 secs"if ((length(glbFeatsDateTime) > 0) &&
(sum(grepl(paste(names(glbFeatsDateTime), "\\.day\\.minutes\\.poly\\.", sep = ""),
names(glbObsAll))) > 0)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.Time.Poly"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars,
grep(paste(names(glbFeatsDateTime), "\\.day\\.minutes\\.poly\\.", sep = ""),
names(glbObsAll), value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Time.Poly",
type = glb_model_type, trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
if ((length(glbFeatsDateTime) > 0) &&
(sum(grepl(paste(names(glbFeatsDateTime), "\\.last[[:digit:]]", sep = ""),
names(glbObsAll))) > 0)) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Max.cor.Y.Time.Lag"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars,
grep(paste(names(glbFeatsDateTime), "\\.last[[:digit:]]", sep = ""),
names(glbObsAll), value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Time.Lag",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
if (length(glbFeatsText) > 0) {
fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
paste0("fit.models_0_", "Txt.*"), major.inc = FALSE,
label.minor = "glmnet")
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.(?!([T|P]\\.))", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.nonTP",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.T\\.", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.onlyT",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
indepVars <- c(max_cor_y_x_vars)
for (txtFeat in names(glbFeatsText))
indepVars <- union(indepVars,
grep(paste(str_to_upper(substr(txtFeat, 1, 1)), "\\.P\\.", sep = ""),
names(glbObsAll), perl = TRUE, value = TRUE))
indepVars <- myadjustInteractionFeats(glb_feats_df, indepVars)
ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = "Max.cor.Y.Text.onlyP",
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = "glmnet")),
indepVar = indepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
# Interactions.High.cor.Y
# Takes a lon time for this case
# if (length(int_feats <- setdiff(setdiff(unique(glb_feats_df$cor.high.X), NA),
# subset(glb_feats_df, nzv)$id)) > 0) {
# fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
# paste0("fit.models_0_", "Interact.High.cor.Y"), major.inc = FALSE,
# label.minor = "glmnet")
#
# ret_lst <- myfit_mdl(mdl_specs_lst=myinit_mdl_specs_lst(mdl_specs_lst=list(
# id.prefix="Interact.High.cor.Y",
# type=glb_model_type, trainControl.method="repeatedcv",
# trainControl.number=glb_rcv_n_folds, trainControl.repeats=glb_rcv_n_repeats,
# trainControl.classProbs = glb_is_classification,
# trainControl.summaryFunction = glbMdlMetricSummaryFn,
# trainControl.allowParallel = glbMdlAllowParallel,
# train.metric = glbMdlMetricSummary,
# train.maximize = glbMdlMetricMaximize,
# train.method="glmnet")),
# indepVar=c(max_cor_y_x_vars, paste(max_cor_y_x_vars[1], int_feats, sep=":")),
# rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB)
# }
# Low.cor.X
# Takes a long time for this case
# fit.models_0_chunk_df <- myadd_chunk(fit.models_0_chunk_df,
# paste0("fit.models_0_", "Low.cor.X"), major.inc = FALSE,
# label.minor = "glmnet")
# indepVar <- mygetIndepVar(glb_feats_df)
# ret_lst <- myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
# id.prefix = "Low.cor.X",
# type = glb_model_type,
# tune.df = glbMdlTuneParams,
# trainControl.method = "repeatedcv",
# trainControl.number = glb_rcv_n_folds, trainControl.repeats = glb_rcv_n_repeats,
# trainControl.classProbs = glb_is_classification,
# trainControl.summaryFunction = glbMdlMetricSummaryFn,
# trainControl.allowParallel = glbMdlAllowParallel,
# train.metric = glbMdlMetricSummary,
# train.maximize = glbMdlMetricMaximize,
# train.method = "glmnet")),
# indepVar = indepVar, rsp_var = glb_rsp_var,
# fit_df = glbObsFit, OOB_df = glbObsOOB)
#
# fit.models_0_chunk_df <-
# myadd_chunk(fit.models_0_chunk_df, "fit.models_0_end", major.inc = FALSE,
# label.minor = "teardown")
rm(ret_lst)
glb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.models", major.inc = FALSE)## label step_major step_minor label_minor bgn end elapsed
## 16 fit.models 8 0 0 118.503 153.03 34.527
## 17 fit.models 8 1 1 153.030 NA NAfit.models_1_chunk_df <- myadd_chunk(NULL, "fit.models_1_bgn", label.minor = "setup")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_1_bgn 1 0 setup 153.862 NA NA# refactor code for outliers / ensure all model runs exclude outliers in this chunk ???
#stop(here"); glb2Sav(); all.equal(glb_models_df, sav_models_df)
topindep_var <- NULL; interact_vars <- NULL;
for (mdl_id_pfx in names(glbMdlFamilies)) {
fit.models_1_chunk_df <-
myadd_chunk(fit.models_1_chunk_df, paste0("fit.models_1_", mdl_id_pfx),
major.inc = FALSE, label.minor = "setup")
indepVar <- NULL;
if (grepl("\\.Interact", mdl_id_pfx)) {
if (is.null(topindep_var) && is.null(interact_vars)) {
# select best glmnet model upto now
dsp_models_df <- orderBy(model_sel_frmla <- get_model_sel_frmla(),
glb_models_df)
dsp_models_df <- subset(dsp_models_df,
grepl(".glmnet", id, fixed = TRUE))
bst_mdl_id <- dsp_models_df$id[1]
mdl_id_pfx <-
paste(c(head(unlist(strsplit(bst_mdl_id, "[.]")), -1), "Interact"),
collapse=".")
# select important features
if (is.null(bst_featsimp_df <-
myget_feats_importance(glb_models_lst[[bst_mdl_id]]))) {
warning("Base model for RFE.Interact: ", bst_mdl_id,
" has no important features")
next
}
topindep_ix <- 1
while (is.null(topindep_var) && (topindep_ix <= nrow(bst_featsimp_df))) {
topindep_var <- row.names(bst_featsimp_df)[topindep_ix]
if (grepl(".fctr", topindep_var, fixed=TRUE))
topindep_var <-
paste0(unlist(strsplit(topindep_var, ".fctr"))[1], ".fctr")
if (topindep_var %in% names(glbFeatsInteractionOnly)) {
topindep_var <- NULL; topindep_ix <- topindep_ix + 1
} else break
}
# select features with importance > max(10, importance of .rnorm) & is not highest
# combine factor dummy features to just the factor feature
if (length(pos_rnorm <-
grep(".rnorm", row.names(bst_featsimp_df), fixed=TRUE)) > 0)
imp_rnorm <- bst_featsimp_df[pos_rnorm, 1] else
imp_rnorm <- NA
imp_cutoff <- max(10, imp_rnorm, na.rm=TRUE)
interact_vars <-
tail(row.names(subset(bst_featsimp_df,
imp > imp_cutoff)), -1)
if (length(interact_vars) > 0) {
interact_vars <-
myadjustInteractionFeats(glb_feats_df, myextract_actual_feats(interact_vars))
interact_vars <-
interact_vars[!grepl(topindep_var, interact_vars, fixed=TRUE)]
}
### bid0_sp only
# interact_vars <- c(
# "biddable", "D.ratio.sum.TfIdf.wrds.n", "D.TfIdf.sum.stem.stop.Ratio", "D.sum.TfIdf",
# "D.TfIdf.sum.post.stop", "D.TfIdf.sum.post.stem", "D.ratio.wrds.stop.n.wrds.n", "D.chrs.uppr.n.log",
# "D.chrs.n.log", "color.fctr"
# # , "condition.fctr", "prdl.my.descr.fctr"
# )
# interact_vars <- setdiff(interact_vars, c("startprice.dgt2.is9", "color.fctr"))
###
indepVar <- myextract_actual_feats(row.names(bst_featsimp_df))
indepVar <- setdiff(indepVar, topindep_var)
if (length(interact_vars) > 0) {
indepVar <-
setdiff(indepVar, myextract_actual_feats(interact_vars))
indepVar <- c(indepVar,
paste(topindep_var, setdiff(interact_vars, topindep_var),
sep = "*"))
} else indepVar <- union(indepVar, topindep_var)
}
}
if (is.null(indepVar))
indepVar <- glb_mdl_feats_lst[[mdl_id_pfx]]
if (is.null(indepVar) && grepl("RFE\\.", mdl_id_pfx))
indepVar <- myextract_actual_feats(predictors(rfe_fit_results))
if (is.null(indepVar))
indepVar <- mygetIndepVar(glb_feats_df)
if ((length(indepVar) == 1) && (grepl("^%<d-%", indepVar))) {
indepVar <-
eval(parse(text = str_trim(unlist(strsplit(indepVar, "%<d-%"))[2])))
}
indepVar <- myadjustInteractionFeats(glb_feats_df, indepVar)
if (grepl("\\.Interact", mdl_id_pfx)) {
# if (method != tail(unlist(strsplit(bst_mdl_id, "[.]")), 1)) next
if (is.null(glbMdlFamilies[[mdl_id_pfx]])) {
if (!is.null(glbMdlFamilies[["Best.Interact"]]))
glbMdlFamilies[[mdl_id_pfx]] <-
glbMdlFamilies[["Best.Interact"]]
}
}
if (!is.null(glbObsFitOutliers[[mdl_id_pfx]])) {
fitobs_df <- glbObsFit[!(glbObsFit[, glbFeatsId] %in%
glbObsFitOutliers[[mdl_id_pfx]]), ]
print(sprintf("Outliers removed: %d", nrow(glbObsFit) - nrow(fitobs_df)))
print(setdiff(glbObsFit[, glbFeatsId], fitobs_df[, glbFeatsId]))
} else fitobs_df <- glbObsFit
if (is.null(glbMdlFamilies[[mdl_id_pfx]]))
mdl_methods <- glbMdlMethods else
mdl_methods <- glbMdlFamilies[[mdl_id_pfx]]
for (method in mdl_methods) {
if (method %in% c("rpart", "rf")) {
# rpart: fubar's the tree
# rf: skip the scenario w/ .rnorm for speed
indepVar <- setdiff(indepVar, c(".rnorm"))
#mdl_id <- paste0(mdl_id_pfx, ".no.rnorm")
}
fit.models_1_chunk_df <- myadd_chunk(fit.models_1_chunk_df,
paste0("fit.models_1_", mdl_id_pfx), major.inc = FALSE,
label.minor = method)
ret_lst <-
myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = mdl_id_pfx,
type = glb_model_type,
tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv", # or "none" if nominalWorkflow is crashing
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = method)),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = fitobs_df, OOB_df = glbObsOOB)
# ntv_mdl <- glmnet(x = as.matrix(
# fitobs_df[, indepVar]),
# y = as.factor(as.character(
# fitobs_df[, glb_rsp_var])),
# family = "multinomial")
# bgn = 1; end = 100;
# ntv_mdl <- glmnet(x = as.matrix(
# subset(fitobs_df, pop.fctr != "crypto")[bgn:end, indepVar]),
# y = as.factor(as.character(
# subset(fitobs_df, pop.fctr != "crypto")[bgn:end, glb_rsp_var])),
# family = "multinomial")
}
}## label step_major step_minor label_minor bgn end
## 1 fit.models_1_bgn 1 0 setup 153.862 153.873
## 2 fit.models_1_All.X 1 1 setup 153.873 NA
## elapsed
## 1 0.011
## 2 NA
## label step_major step_minor label_minor bgn end
## 2 fit.models_1_All.X 1 1 setup 153.873 153.88
## 3 fit.models_1_All.X 1 2 glmnet 153.880 NA
## elapsed
## 2 0.007
## 3 NA
## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: All.X##rcv#glmnet"
## [1] " indepVar: Age,Married.fctr,Education.fctr,Region.fctr,Race.fctr,.rnorm,Citizenship.fctr,Hispanic,Sex.fctr,PeopleInHousehold"
## [1] "myfit_mdl: setup complete: 0.732000 secs"
## + Fold1.Rep1: alpha=0.100, lambda=0.1012
## - Fold1.Rep1: alpha=0.100, lambda=0.1012
## + Fold1.Rep1: alpha=0.325, lambda=0.1012
## - Fold1.Rep1: alpha=0.325, lambda=0.1012
## + Fold1.Rep1: alpha=0.550, lambda=0.1012
## - Fold1.Rep1: alpha=0.550, lambda=0.1012
## + Fold1.Rep1: alpha=0.775, lambda=0.1012
## - Fold1.Rep1: alpha=0.775, lambda=0.1012
## + Fold1.Rep1: alpha=1.000, lambda=0.1012
## - Fold1.Rep1: alpha=1.000, lambda=0.1012
## + Fold2.Rep1: alpha=0.100, lambda=0.1012
## - Fold2.Rep1: alpha=0.100, lambda=0.1012
## + Fold2.Rep1: alpha=0.325, lambda=0.1012
## - Fold2.Rep1: alpha=0.325, lambda=0.1012
## + Fold2.Rep1: alpha=0.550, lambda=0.1012
## - Fold2.Rep1: alpha=0.550, lambda=0.1012
## + Fold2.Rep1: alpha=0.775, lambda=0.1012
## - Fold2.Rep1: alpha=0.775, lambda=0.1012
## + Fold2.Rep1: alpha=1.000, lambda=0.1012
## - Fold2.Rep1: alpha=1.000, lambda=0.1012
## + Fold3.Rep1: alpha=0.100, lambda=0.1012
## - Fold3.Rep1: alpha=0.100, lambda=0.1012
## + Fold3.Rep1: alpha=0.325, lambda=0.1012
## - Fold3.Rep1: alpha=0.325, lambda=0.1012
## + Fold3.Rep1: alpha=0.550, lambda=0.1012
## - Fold3.Rep1: alpha=0.550, lambda=0.1012
## + Fold3.Rep1: alpha=0.775, lambda=0.1012
## - Fold3.Rep1: alpha=0.775, lambda=0.1012
## + Fold3.Rep1: alpha=1.000, lambda=0.1012
## - Fold3.Rep1: alpha=1.000, lambda=0.1012
## + Fold1.Rep2: alpha=0.100, lambda=0.1012
## - Fold1.Rep2: alpha=0.100, lambda=0.1012
## + Fold1.Rep2: alpha=0.325, lambda=0.1012
## - Fold1.Rep2: alpha=0.325, lambda=0.1012
## + Fold1.Rep2: alpha=0.550, lambda=0.1012
## - Fold1.Rep2: alpha=0.550, lambda=0.1012
## + Fold1.Rep2: alpha=0.775, lambda=0.1012
## - Fold1.Rep2: alpha=0.775, lambda=0.1012
## + Fold1.Rep2: alpha=1.000, lambda=0.1012
## - Fold1.Rep2: alpha=1.000, lambda=0.1012
## + Fold2.Rep2: alpha=0.100, lambda=0.1012
## - Fold2.Rep2: alpha=0.100, lambda=0.1012
## + Fold2.Rep2: alpha=0.325, lambda=0.1012
## - Fold2.Rep2: alpha=0.325, lambda=0.1012
## + Fold2.Rep2: alpha=0.550, lambda=0.1012
## - Fold2.Rep2: alpha=0.550, lambda=0.1012
## + Fold2.Rep2: alpha=0.775, lambda=0.1012
## - Fold2.Rep2: alpha=0.775, lambda=0.1012
## + Fold2.Rep2: alpha=1.000, lambda=0.1012
## - Fold2.Rep2: alpha=1.000, lambda=0.1012
## + Fold3.Rep2: alpha=0.100, lambda=0.1012
## - Fold3.Rep2: alpha=0.100, lambda=0.1012
## + Fold3.Rep2: alpha=0.325, lambda=0.1012
## - Fold3.Rep2: alpha=0.325, lambda=0.1012
## + Fold3.Rep2: alpha=0.550, lambda=0.1012
## - Fold3.Rep2: alpha=0.550, lambda=0.1012
## + Fold3.Rep2: alpha=0.775, lambda=0.1012
## - Fold3.Rep2: alpha=0.775, lambda=0.1012
## + Fold3.Rep2: alpha=1.000, lambda=0.1012
## - Fold3.Rep2: alpha=1.000, lambda=0.1012
## + Fold1.Rep3: alpha=0.100, lambda=0.1012
## - Fold1.Rep3: alpha=0.100, lambda=0.1012
## + Fold1.Rep3: alpha=0.325, lambda=0.1012
## - Fold1.Rep3: alpha=0.325, lambda=0.1012
## + Fold1.Rep3: alpha=0.550, lambda=0.1012
## - Fold1.Rep3: alpha=0.550, lambda=0.1012
## + Fold1.Rep3: alpha=0.775, lambda=0.1012
## - Fold1.Rep3: alpha=0.775, lambda=0.1012
## + Fold1.Rep3: alpha=1.000, lambda=0.1012
## - Fold1.Rep3: alpha=1.000, lambda=0.1012
## + Fold2.Rep3: alpha=0.100, lambda=0.1012
## - Fold2.Rep3: alpha=0.100, lambda=0.1012
## + Fold2.Rep3: alpha=0.325, lambda=0.1012
## - Fold2.Rep3: alpha=0.325, lambda=0.1012
## + Fold2.Rep3: alpha=0.550, lambda=0.1012
## - Fold2.Rep3: alpha=0.550, lambda=0.1012
## + Fold2.Rep3: alpha=0.775, lambda=0.1012
## - Fold2.Rep3: alpha=0.775, lambda=0.1012
## + Fold2.Rep3: alpha=1.000, lambda=0.1012
## - Fold2.Rep3: alpha=1.000, lambda=0.1012
## + Fold3.Rep3: alpha=0.100, lambda=0.1012
## - Fold3.Rep3: alpha=0.100, lambda=0.1012
## + Fold3.Rep3: alpha=0.325, lambda=0.1012
## - Fold3.Rep3: alpha=0.325, lambda=0.1012
## + Fold3.Rep3: alpha=0.550, lambda=0.1012
## - Fold3.Rep3: alpha=0.550, lambda=0.1012
## + Fold3.Rep3: alpha=0.775, lambda=0.1012
## - Fold3.Rep3: alpha=0.775, lambda=0.1012
## + Fold3.Rep3: alpha=1.000, lambda=0.1012
## - Fold3.Rep3: alpha=1.000, lambda=0.1012
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 1, lambda = 0.000218 on full training set
## [1] "myfit_mdl: train complete: 1120.893000 secs"## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = mdl_id_pfx, : model's bestTune found at an extreme of
## tuneGrid for parameter: alpha## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = mdl_id_pfx, : model's bestTune found at an extreme of
## tuneGrid for parameter: lambda
## Length Class Mode
## a0 380 -none- numeric
## beta 5 -none- list
## dfmat 380 -none- numeric
## df 76 -none- numeric
## dim 2 -none- numeric
## lambda 76 -none- numeric
## dev.ratio 76 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 5 -none- character
## grouped 1 -none- logical
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 28 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 5 -none- character
## [1] "min lambda > lambdaOpt:"
## [1] "class: Disabled:"
##
## -0.682133676
## .rnorm
## 0.016236821
## Age
## 0.052704231
## Citizenship.fctrCitizen, Naturalized
## -0.505511515
## Citizenship.fctrNon-Citizen
## -0.860459043
## Education.fctrBachelor's degree
## -0.629820356
## Education.fctrDoctorate degree
## -0.626569025
## Education.fctrHigh school
## 0.362734617
## Education.fctrMaster's degree
## -0.868888624
## Education.fctrNo high school diploma
## 1.064677342
## Education.fctrProfessional degree
## -0.757369329
## Education.fctrSome college, no degree
## 0.115647622
## Married.fctrMarried
## -0.857965891
## Married.fctrSeparated
## 0.160275744
## PeopleInHousehold
## -0.016579180
## Race.fctrAmerican Indian
## 0.009019554
## Race.fctrAsian
## -0.072868661
## Race.fctrBlack
## 0.310408699
## Race.fctrMultiracial
## 0.092364638
## Race.fctrPacific Islander
## 0.275381398
## Region.fctrMidwest
## -0.071696043
## Region.fctrNortheast
## -0.016321483
## Region.fctrWest
## -0.105253659
## [1] "class: Employed:"
##
## 4.07376570
## .rnorm
## 0.01129780
## Citizenship.fctrCitizen, Naturalized
## 0.08291596
## Citizenship.fctrNon-Citizen
## 0.07695471
## Education.fctrBachelor's degree
## 0.15279080
## Education.fctrDoctorate degree
## 0.76855035
## Education.fctrHigh school
## -0.45606953
## Education.fctrMaster's degree
## 0.25793173
## Education.fctrNo high school diploma
## -0.85274987
## Education.fctrProfessional degree
## 0.53560074
## Education.fctrSome college, no degree
## -0.21721324
## Hispanic
## 0.05415627
## Married.fctrNever Married
## -0.20637501
## Married.fctrWidowed
## -0.11773377
## Race.fctrAmerican Indian
## -0.36911791
## Race.fctrBlack
## -0.20263429
## Race.fctrMultiracial
## -0.12817419
## Race.fctrPacific Islander
## -0.15995753
## Region.fctrMidwest
## 0.14673165
## Region.fctrNortheast
## 0.08782864
## Sex.fctrMale
## 0.22191720
## [1] "class: Not.in.Labor.Force:"
##
## 3.24612651
## Age
## -0.04130075
## Citizenship.fctrCitizen, Naturalized
## 0.04137445
## Citizenship.fctrNon-Citizen
## 0.15887442
## Education.fctrMaster's degree
## -0.04074203
## Education.fctrNo high school diploma
## 0.96791390
## Education.fctrSome college, no degree
## 0.23005093
## Hispanic
## -0.10370630
## Married.fctrMarried
## 0.25953648
## Married.fctrNever Married
## 0.33375203
## Married.fctrSeparated
## -0.03752998
## Married.fctrWidowed
## 0.58309739
## PeopleInHousehold
## 0.14682379
## Race.fctrAsian
## 0.43940282
## Race.fctrBlack
## -0.09106900
## Race.fctrMultiracial
## 0.05427560
## Region.fctrMidwest
## -0.14995281
## Sex.fctrMale
## -0.71644104
## [1] "class: Retired:"
## .rnorm
## -7.766237327 -0.016588779
## Age Citizenship.fctrCitizen, Naturalized
## 0.180449160 -0.210603156
## Citizenship.fctrNon-Citizen Education.fctrBachelor's degree
## -0.291485719 0.041172954
## Education.fctrDoctorate degree Education.fctrHigh school
## 0.034833709 -0.076053875
## Education.fctrMaster's degree Married.fctrMarried
## 0.235914499 0.408448441
## Married.fctrNever Married Married.fctrSeparated
## -0.049324597 -0.215449376
## Married.fctrWidowed PeopleInHousehold
## 0.527580786 -0.159180446
## Race.fctrAmerican Indian Race.fctrAsian
## -0.180429213 0.149154928
## Race.fctrMultiracial Race.fctrPacific Islander
## -0.112375180 -0.184683057
## Region.fctrNortheast Region.fctrWest
## -0.001068302 0.080242502
## Sex.fctrMale
## -0.112094049
## [1] "class: Unemployed:"
##
## 1.128478797
## Age
## -0.003594189
## Education.fctrHigh school
## 0.006293782
## Education.fctrNo high school diploma
## -0.117670195
## Education.fctrSome college, no degree
## -0.003394560
## Hispanic
## 0.171124677
## Married.fctrMarried
## -0.539803262
## Married.fctrNever Married
## 0.026250406
## Married.fctrSeparated
## 0.056433648
## Married.fctrWidowed
## -0.113801986
## PeopleInHousehold
## 0.071712840
## Race.fctrAmerican Indian
## 0.226698090
## Race.fctrAsian
## -0.055242748
## Race.fctrBlack
## 0.499911437
## Race.fctrPacific Islander
## 0.027777413
## Region.fctrMidwest
## 0.034678764
## Region.fctrNortheast
## 0.151019068
## Region.fctrWest
## 0.091052386
## Sex.fctrMale
## 0.229847065
## [1] "max lambda < lambdaOpt:"
## [1] "Feats mismatch between coefs_left & rght:"
## [1] ""
## [2] ".rnorm"
## [3] "Age"
## [4] "Citizenship.fctrCitizen, Naturalized"
## [5] "Citizenship.fctrNon-Citizen"
## [6] "Education.fctrBachelor's degree"
## [7] "Education.fctrDoctorate degree"
## [8] "Education.fctrHigh school"
## [9] "Education.fctrMaster's degree"
## [10] "Education.fctrNA.my"
## [11] "Education.fctrNo high school diploma"
## [12] "Education.fctrProfessional degree"
## [13] "Education.fctrSome college, no degree"
## [14] "Hispanic"
## [15] "Married.fctrMarried"
## [16] "Married.fctrNA.my"
## [17] "Married.fctrNever Married"
## [18] "Married.fctrSeparated"
## [19] "Married.fctrWidowed"
## [20] "PeopleInHousehold"
## [21] "Race.fctrAmerican Indian"
## [22] "Race.fctrAsian"
## [23] "Race.fctrBlack"
## [24] "Race.fctrMultiracial"
## [25] "Race.fctrPacific Islander"
## [26] "Region.fctrMidwest"
## [27] "Region.fctrNortheast"
## [28] "Region.fctrWest"
## [29] "Sex.fctrMale"
## [1] "myfit_mdl: train diagnostics complete: 1122.250000 secs"
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 194 3181 201 600
## Employed 90 41243 1636 2166
## Not.in.Labor.Force 36 6522 4301 288
## Retired 83 3387 20 10123
## Unemployed 13 2580 360 119
## Prediction
## Reference Unemployed
## Disabled 0
## Employed 0
## Not.in.Labor.Force 0
## Retired 0
## Unemployed 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.7241227 0.4749539 0.7209538 0.7272748 0.5850822
## AccuracyPValue McnemarPValue
## 0.0000000 0.0000000
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 82 1169 70 215
## Employed 50 15141 614 793
## Not.in.Labor.Force 17 2429 1545 108
## Retired 26 1234 5 3741
## Unemployed 6 948 150 27
## Prediction
## Reference Unemployed
## Disabled 0
## Employed 0
## Not.in.Labor.Force 0
## Retired 0
## Unemployed 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.7229115 0.4729121 0.7176633 0.7281141 0.5850546
## AccuracyPValue McnemarPValue
## 0.0000000 0.0000000
## [1] "myfit_mdl: predict complete: 1124.230000 secs"
## id
## 1 All.X##rcv#glmnet
## feats
## 1 Age,Married.fctr,Education.fctr,Region.fctr,Race.fctr,.rnorm,Citizenship.fctr,Hispanic,Sex.fctr,PeopleInHousehold
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 1119.977 32.992
## max.Accuracy.fit max.AccuracyLower.fit max.AccuracyUpper.fit
## 1 0.7235826 0.7209538 0.7272748
## max.Kappa.fit max.Accuracy.OOB max.AccuracyLower.OOB
## 1 0.4737991 0.7229115 0.7176633
## max.AccuracyUpper.OOB max.Kappa.OOB max.AccuracySD.fit max.KappaSD.fit
## 1 0.7281141 0.4729121 0.002280983 0.004205104
## [1] "myfit_mdl: exit: 1124.239000 secs"# Check if other preProcess methods improve model performance
fit.models_1_chunk_df <-
myadd_chunk(fit.models_1_chunk_df, "fit.models_1_preProc", major.inc = FALSE,
label.minor = "preProc")## label step_major step_minor label_minor bgn end
## 3 fit.models_1_All.X 1 2 glmnet 153.880 1278.131
## 4 fit.models_1_preProc 1 3 preProc 1278.132 NA
## elapsed
## 3 1124.251
## 4 NAmdl_id <- orderBy(get_model_sel_frmla(), glb_models_df)[1, "id"]
indepVar <- trim(unlist(strsplit(glb_models_df[glb_models_df$id == mdl_id,
"feats"], "[,]")))
method <- tail(unlist(strsplit(mdl_id, "[.]")), 1)
mdl_id_pfx <- paste0(head(unlist(strsplit(mdl_id, "[.]")), -1), collapse = ".")
if (!is.null(glbObsFitOutliers[[mdl_id_pfx]])) {
fitobs_df <- glbObsFit[!(glbObsFit[, glbFeatsId] %in%
glbObsFitOutliers[[mdl_id_pfx]]), ]
print(sprintf("Outliers removed: %d", nrow(glbObsFit) - nrow(fitobs_df)))
print(setdiff(glbObsFit[, glbFeatsId], fitobs_df[, glbFeatsId]))
} else fitobs_df <- glbObsFit
for (prePr in glb_preproc_methods) {
# The operations are applied in this order:
# Box-Cox/Yeo-Johnson transformation, centering, scaling, range, imputation, PCA, ICA then spatial sign.
ret_lst <- myfit_mdl(mdl_specs_lst=myinit_mdl_specs_lst(mdl_specs_lst=list(
id.prefix=mdl_id_pfx,
type=glb_model_type, tune.df=glbMdlTuneParams,
trainControl.method="repeatedcv",
trainControl.number=glb_rcv_n_folds,
trainControl.repeats=glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method=method, train.preProcess=prePr)),
indepVar=indepVar, rsp_var=glb_rsp_var,
fit_df=fitobs_df, OOB_df=glbObsOOB)
}
# If (All|RFE).X.glm is less accurate than Low.Cor.X.glm
# check NA coefficients & filter appropriate terms in indepVar
# if (method == "glm") {
# orig_glm <- glb_models_lst[[paste0(mdl_id, ".", model_method)]]$finalModel
# orig_glm <- glb_models_lst[["All.X.glm"]]$finalModel; print(summary(orig_glm))
# orig_glm <- glb_models_lst[["RFE.X.glm"]]$finalModel; print(summary(orig_glm))
# require(car)
# vif_orig_glm <- vif(orig_glm); print(vif_orig_glm)
# # if vif errors out with "there are aliased coefficients in the model"
# alias_orig_glm <- alias(orig_glm); alias_complete_orig_glm <- (alias_orig_glm$Complete > 0); alias_complete_orig_glm <- alias_complete_orig_glm[rowSums(alias_complete_orig_glm) > 0, colSums(alias_complete_orig_glm) > 0]; print(alias_complete_orig_glm)
# print(vif_orig_glm[!is.na(vif_orig_glm) & (vif_orig_glm == Inf)])
# print(which.max(vif_orig_glm))
# print(sort(vif_orig_glm[vif_orig_glm >= 1.0e+03], decreasing=TRUE))
# glbObsFit[c(1143, 3637, 3953, 4105), c("UniqueID", "Popular", "H.P.quandary", "Headline")]
# glb_feats_df[glb_feats_df$id %in% grep("[HSA]\\.chrs.n.log", glb_feats_df$id, value=TRUE) | glb_feats_df$cor.high.X %in% grep("[HSA]\\.chrs.n.log", glb_feats_df$id, value=TRUE), ]
# all.equal(glbObsAll$S.chrs.uppr.n.log, glbObsAll$A.chrs.uppr.n.log)
# cor(glbObsAll$S.T.herald, glbObsAll$S.T.tribun)
# mydspObs(Abstract.contains="[Dd]iar", cols=("Abstract"), all=TRUE)
# subset(glb_feats_df, cor.y.abs <= glb_feats_df[glb_feats_df$id == ".rnorm", "cor.y.abs"])
# corxx_mtrx <- cor(data.matrix(glbObsAll[, setdiff(names(glbObsAll), myfind_chr_cols_df(glbObsAll))]), use="pairwise.complete.obs"); abs_corxx_mtrx <- abs(corxx_mtrx); diag(abs_corxx_mtrx) <- 0
# which.max(abs_corxx_mtrx["S.T.tribun", ])
# abs_corxx_mtrx["A.npnct08.log", "S.npnct08.log"]
# step_glm <- step(orig_glm)
# }
# Since caret does not optimize rpart well
# if (method == "rpart")
# ret_lst <- myfit_mdl(mdl_id=paste0(mdl_id_pfx, ".cp.0"), model_method=method,
# indepVar=indepVar,
# model_type=glb_model_type,
# rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB,
# n_cv_folds=0, tune_models_df=data.frame(parameter="cp", min=0.0, max=0.0, by=0.1))
# User specified
# Ensure at least 2 vars in each regression; else varImp crashes
# sav_models_lst <- glb_models_lst; sav_models_df <- glb_models_df; sav_featsimp_df <- glb_featsimp_df; all.equal(sav_featsimp_df, glb_featsimp_df)
# glb_models_lst <- sav_models_lst; glb_models_df <- sav_models_df; glm_featsimp_df <- sav_featsimp_df
# easier to exclude features
# require(gdata) # needed for trim
# mdl_id <- "";
# indepVar <- head(subset(glb_models_df, grepl("All\\.X\\.", mdl_id), select=feats)
# , 1)[, "feats"]
# indepVar <- trim(unlist(strsplit(indepVar, "[,]")))
# indepVar <- setdiff(indepVar, ".rnorm")
# easier to include features
#stop(here"); sav_models_df <- glb_models_df; glb_models_df <- sav_models_df
# !_sp
# mdl_id <- "csm"; indepVar <- c(NULL
# ,"prdline.my.fctr", "prdline.my.fctr:.clusterid.fctr"
# ,"prdline.my.fctr*biddable"
# #,"prdline.my.fctr*startprice.log"
# #,"prdline.my.fctr*startprice.diff"
# ,"prdline.my.fctr*condition.fctr"
# ,"prdline.my.fctr*D.terms.post.stop.n"
# #,"prdline.my.fctr*D.terms.post.stem.n"
# ,"prdline.my.fctr*cellular.fctr"
# # ,"<feat1>:<feat2>"
# )
# for (method in glbMdlMethods) {
# ret_lst <- myfit_mdl(mdl_id=mdl_id, model_method=method,
# indepVar=indepVar,
# model_type=glb_model_type,
# rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB,
# n_cv_folds=glb_rcv_n_folds, tune_models_df=glbMdlTuneParams)
# csm_mdl_id <- paste0(mdl_id, ".", method)
# csm_featsimp_df <- myget_feats_importance(glb_models_lst[[paste0(mdl_id, ".",
# method)]]); print(head(csm_featsimp_df))
# }
###
# Ntv.1.lm <- lm(reformulate(indepVar, glb_rsp_var), glbObsTrn); print(summary(Ntv.1.lm))
#glb_models_df[, "max.Accuracy.OOB", FALSE]
#varImp(glb_models_lst[["Low.cor.X.glm"]])
#orderBy(~ -Overall, varImp(glb_models_lst[["All.X.2.glm"]])$imp)
#orderBy(~ -Overall, varImp(glb_models_lst[["All.X.3.glm"]])$imp)
#glb_feats_df[grepl("npnct28", glb_feats_df$id), ]
# User specified bivariate models
# indepVar_lst <- list()
# for (feat in setdiff(names(glbObsFit),
# union(glb_rsp_var, glbFeatsExclude)))
# indepVar_lst[["feat"]] <- feat
# User specified combinatorial models
# indepVar_lst <- list()
# combn_mtrx <- combn(c("<feat1_name>", "<feat2_name>", "<featn_name>"),
# <num_feats_to_choose>)
# for (combn_ix in 1:ncol(combn_mtrx))
# #print(combn_mtrx[, combn_ix])
# indepVar_lst[[combn_ix]] <- combn_mtrx[, combn_ix]
# template for myfit_mdl
# rf is hard-coded in caret to recognize only Accuracy / Kappa evaluation metrics
# only for OOB in trainControl ?
# ret_lst <- myfit_mdl_fn(mdl_id=paste0(mdl_id_pfx, ""), model_method=method,
# indepVar=indepVar,
# rsp_var=glb_rsp_var,
# fit_df=glbObsFit, OOB_df=glbObsOOB,
# n_cv_folds=glb_rcv_n_folds, tune_models_df=glbMdlTuneParams,
# model_loss_mtrx=glbMdlMetric_terms,
# model_summaryFunction=glbMdlMetricSummaryFn,
# model_metric=glbMdlMetricSummary,
# model_metric_maximize=glbMdlMetricMaximize)
# Simplify a model
# fit_df <- glbObsFit; glb_mdl <- step(<complex>_mdl)
# Non-caret models
# rpart_area_mdl <- rpart(reformulate("Area", response=glb_rsp_var),
# data=glbObsFit, #method="class",
# control=rpart.control(cp=0.12),
# parms=list(loss=glbMdlMetric_terms))
# print("rpart_sel_wlm_mdl"); prp(rpart_sel_wlm_mdl)
#
print(glb_models_df)## id
## MFO###myMFO_classfr MFO###myMFO_classfr
## Random###myrandom_classfr Random###myrandom_classfr
## Max.cor.Y.rcv.1X1###glmnet Max.cor.Y.rcv.1X1###glmnet
## Max.cor.Y##rcv#rpart Max.cor.Y##rcv#rpart
## All.X##rcv#glmnet All.X##rcv#glmnet
## feats
## MFO###myMFO_classfr .rnorm
## Random###myrandom_classfr .rnorm
## Max.cor.Y.rcv.1X1###glmnet Age,Married.fctr
## Max.cor.Y##rcv#rpart Age,Married.fctr
## All.X##rcv#glmnet Age,Married.fctr,Education.fctr,Region.fctr,Race.fctr,.rnorm,Citizenship.fctr,Hispanic,Sex.fctr,PeopleInHousehold
## max.nTuningRuns min.elapsedtime.everything
## MFO###myMFO_classfr 0 0.484
## Random###myrandom_classfr 0 0.336
## Max.cor.Y.rcv.1X1###glmnet 0 12.169
## Max.cor.Y##rcv#rpart 5 14.705
## All.X##rcv#glmnet 25 1119.977
## min.elapsedtime.final max.Accuracy.fit
## MFO###myMFO_classfr 0.020 0.5850822
## Random###myrandom_classfr 0.017 0.3996604
## Max.cor.Y.rcv.1X1###glmnet 10.348 0.6842487
## Max.cor.Y##rcv#rpart 0.399 0.7264431
## All.X##rcv#glmnet 32.992 0.7235826
## max.AccuracyLower.fit max.AccuracyUpper.fit
## MFO###myMFO_classfr 0.5815957 0.5885624
## Random###myrandom_classfr 0.3962012 0.4031271
## Max.cor.Y.rcv.1X1###glmnet 0.6809553 0.6875283
## Max.cor.Y##rcv#rpart 0.7239458 0.7302455
## All.X##rcv#glmnet 0.7209538 0.7272748
## max.Kappa.fit max.Accuracy.OOB
## MFO###myMFO_classfr 0.000000000 0.5850546
## Random###myrandom_classfr 0.001664263 0.3991540
## Max.cor.Y.rcv.1X1###glmnet 0.344662905 0.6859711
## Max.cor.Y##rcv#rpart 0.477125106 0.7276701
## All.X##rcv#glmnet 0.473799092 0.7229115
## max.AccuracyLower.OOB max.AccuracyUpper.OOB
## MFO###myMFO_classfr 0.5792951 0.5907967
## Random###myrandom_classfr 0.3934484 0.4048804
## Max.cor.Y.rcv.1X1###glmnet 0.6805339 0.6913702
## Max.cor.Y##rcv#rpart 0.7224493 0.7328442
## All.X##rcv#glmnet 0.7176633 0.7281141
## max.Kappa.OOB max.AccuracySD.fit
## MFO###myMFO_classfr 0.0000000000 NA
## Random###myrandom_classfr 0.0006568311 NA
## Max.cor.Y.rcv.1X1###glmnet 0.3481272164 NA
## Max.cor.Y##rcv#rpart 0.4783438508 0.002327336
## All.X##rcv#glmnet 0.4729121383 0.002280983
## max.KappaSD.fit
## MFO###myMFO_classfr NA
## Random###myrandom_classfr NA
## Max.cor.Y.rcv.1X1###glmnet NA
## Max.cor.Y##rcv#rpart 0.005671842
## All.X##rcv#glmnet 0.004205104rm(ret_lst)
fit.models_1_chunk_df <-
myadd_chunk(fit.models_1_chunk_df, "fit.models_1_end", major.inc = FALSE,
label.minor = "teardown")## label step_major step_minor label_minor bgn end
## 4 fit.models_1_preProc 1 3 preProc 1278.132 1278.187
## 5 fit.models_1_end 1 4 teardown 1278.188 NA
## elapsed
## 4 0.055
## 5 NAglb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.models", major.inc = FALSE)## label step_major step_minor label_minor bgn end elapsed
## 17 fit.models 8 1 1 153.030 1278.195 1125.166
## 18 fit.models 8 2 2 1278.196 NA NAfit.models_2_chunk_df <-
myadd_chunk(NULL, "fit.models_2_bgn", label.minor = "setup")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_2_bgn 1 0 setup 1279.567 NA NAplt_models_df <- glb_models_df[, -grep("SD|Upper|Lower", names(glb_models_df))]
for (var in grep("^min.", names(plt_models_df), value=TRUE)) {
plt_models_df[, sub("min.", "inv.", var)] <-
#ifelse(all(is.na(tmp <- plt_models_df[, var])), NA, 1.0 / tmp)
1.0 / plt_models_df[, var]
plt_models_df <- plt_models_df[ , -grep(var, names(plt_models_df))]
}
print(plt_models_df)## id
## MFO###myMFO_classfr MFO###myMFO_classfr
## Random###myrandom_classfr Random###myrandom_classfr
## Max.cor.Y.rcv.1X1###glmnet Max.cor.Y.rcv.1X1###glmnet
## Max.cor.Y##rcv#rpart Max.cor.Y##rcv#rpart
## All.X##rcv#glmnet All.X##rcv#glmnet
## feats
## MFO###myMFO_classfr .rnorm
## Random###myrandom_classfr .rnorm
## Max.cor.Y.rcv.1X1###glmnet Age,Married.fctr
## Max.cor.Y##rcv#rpart Age,Married.fctr
## All.X##rcv#glmnet Age,Married.fctr,Education.fctr,Region.fctr,Race.fctr,.rnorm,Citizenship.fctr,Hispanic,Sex.fctr,PeopleInHousehold
## max.nTuningRuns max.Accuracy.fit max.Kappa.fit
## MFO###myMFO_classfr 0 0.5850822 0.000000000
## Random###myrandom_classfr 0 0.3996604 0.001664263
## Max.cor.Y.rcv.1X1###glmnet 0 0.6842487 0.344662905
## Max.cor.Y##rcv#rpart 5 0.7264431 0.477125106
## All.X##rcv#glmnet 25 0.7235826 0.473799092
## max.Accuracy.OOB max.Kappa.OOB
## MFO###myMFO_classfr 0.5850546 0.0000000000
## Random###myrandom_classfr 0.3991540 0.0006568311
## Max.cor.Y.rcv.1X1###glmnet 0.6859711 0.3481272164
## Max.cor.Y##rcv#rpart 0.7276701 0.4783438508
## All.X##rcv#glmnet 0.7229115 0.4729121383
## inv.elapsedtime.everything
## MFO###myMFO_classfr 2.0661157025
## Random###myrandom_classfr 2.9761904762
## Max.cor.Y.rcv.1X1###glmnet 0.0821760210
## Max.cor.Y##rcv#rpart 0.0680040802
## All.X##rcv#glmnet 0.0008928755
## inv.elapsedtime.final
## MFO###myMFO_classfr 50.00000000
## Random###myrandom_classfr 58.82352941
## Max.cor.Y.rcv.1X1###glmnet 0.09663703
## Max.cor.Y##rcv#rpart 2.50626566
## All.X##rcv#glmnet 0.03031038# print(myplot_radar(radar_inp_df=plt_models_df))
# print(myplot_radar(radar_inp_df=subset(plt_models_df,
# !(mdl_id %in% grep("random|MFO", plt_models_df$id, value=TRUE)))))
# Compute CI for <metric>SD
glb_models_df <- mutate(glb_models_df,
max.df = ifelse(max.nTuningRuns > 1, max.nTuningRuns - 1, NA),
min.sd2ci.scaler = ifelse(is.na(max.df), NA, qt(0.975, max.df)))
for (var in grep("SD", names(glb_models_df), value=TRUE)) {
# Does CI alredy exist ?
var_components <- unlist(strsplit(var, "SD"))
varActul <- paste0(var_components[1], var_components[2])
varUpper <- paste0(var_components[1], "Upper", var_components[2])
varLower <- paste0(var_components[1], "Lower", var_components[2])
if (varUpper %in% names(glb_models_df)) {
warning(varUpper, " already exists in glb_models_df")
# Assuming Lower also exists
next
}
print(sprintf("var:%s", var))
# CI is dependent on sample size in t distribution; df=n-1
glb_models_df[, varUpper] <- glb_models_df[, varActul] +
glb_models_df[, "min.sd2ci.scaler"] * glb_models_df[, var]
glb_models_df[, varLower] <- glb_models_df[, varActul] -
glb_models_df[, "min.sd2ci.scaler"] * glb_models_df[, var]
}## Warning: max.AccuracyUpper.fit already exists in glb_models_df## [1] "var:max.KappaSD.fit"# Plot metrics with CI
plt_models_df <- glb_models_df[, "id", FALSE]
pltCI_models_df <- glb_models_df[, "id", FALSE]
for (var in grep("Upper", names(glb_models_df), value=TRUE)) {
var_components <- unlist(strsplit(var, "Upper"))
col_name <- unlist(paste(var_components, collapse=""))
plt_models_df[, col_name] <- glb_models_df[, col_name]
for (name in paste0(var_components[1], c("Upper", "Lower"), var_components[2]))
pltCI_models_df[, name] <- glb_models_df[, name]
}
build_statsCI_data <- function(plt_models_df) {
mltd_models_df <- melt(plt_models_df, id.vars="id")
mltd_models_df$data <- sapply(1:nrow(mltd_models_df),
function(row_ix) tail(unlist(strsplit(as.character(
mltd_models_df[row_ix, "variable"]), "[.]")), 1))
mltd_models_df$label <- sapply(1:nrow(mltd_models_df),
function(row_ix) head(unlist(strsplit(as.character(
mltd_models_df[row_ix, "variable"]),
paste0(".", mltd_models_df[row_ix, "data"]))), 1))
#print(mltd_models_df)
return(mltd_models_df)
}
mltd_models_df <- build_statsCI_data(plt_models_df)
mltdCI_models_df <- melt(pltCI_models_df, id.vars="id")
for (row_ix in 1:nrow(mltdCI_models_df)) {
for (type in c("Upper", "Lower")) {
if (length(var_components <- unlist(strsplit(
as.character(mltdCI_models_df[row_ix, "variable"]), type))) > 1) {
#print(sprintf("row_ix:%d; type:%s; ", row_ix, type))
mltdCI_models_df[row_ix, "label"] <- var_components[1]
mltdCI_models_df[row_ix, "data"] <-
unlist(strsplit(var_components[2], "[.]"))[2]
mltdCI_models_df[row_ix, "type"] <- type
break
}
}
}
wideCI_models_df <- reshape(subset(mltdCI_models_df, select=-variable),
timevar="type",
idvar=setdiff(names(mltdCI_models_df), c("type", "value", "variable")),
direction="wide")
#print(wideCI_models_df)
mrgdCI_models_df <- merge(wideCI_models_df, mltd_models_df, all.x=TRUE)
#print(mrgdCI_models_df)
# Merge stats back in if CIs don't exist
goback_vars <- c()
for (var in unique(mltd_models_df$label)) {
for (type in unique(mltd_models_df$data)) {
var_type <- paste0(var, ".", type)
# if this data is already present, next
if (var_type %in% unique(paste(mltd_models_df$label, mltd_models_df$data,
sep=".")))
next
#print(sprintf("var_type:%s", var_type))
goback_vars <- c(goback_vars, var_type)
}
}
if (length(goback_vars) > 0) {
mltd_goback_df <- build_statsCI_data(glb_models_df[, c("id", goback_vars)])
mltd_models_df <- rbind(mltd_models_df, mltd_goback_df)
}
# mltd_models_df <- merge(mltd_models_df, glb_models_df[, c("id", "model_method")],
# all.x=TRUE)
png(paste0(glbOut$pfx, "models_bar.png"), width=480*3, height=480*2)
#print(gp <- myplot_bar(mltd_models_df, "id", "value", colorcol_name="model_method") +
print(gp <- myplot_bar(df=mltd_models_df, xcol_name="id", ycol_names="value") +
geom_errorbar(data=mrgdCI_models_df,
mapping=aes(x=mdl_id, ymax=value.Upper, ymin=value.Lower), width=0.5) +
facet_grid(label ~ data, scales="free") +
theme(axis.text.x = element_text(angle = 90,vjust = 0.5)))## Warning: Removed 3 rows containing missing values (geom_errorbar).dev.off()## quartz_off_screen
## 2print(gp)## Warning: Removed 3 rows containing missing values (geom_errorbar).
dsp_models_cols <- c("id",
glbMdlMetricsEval[glbMdlMetricsEval %in% names(glb_models_df)],
grep("opt.", names(glb_models_df), fixed = TRUE, value = TRUE))
# if (glb_is_classification && glb_is_binomial)
# dsp_models_cols <- c(dsp_models_cols, "opt.prob.threshold.OOB")
print(dsp_models_df <- orderBy(get_model_sel_frmla(), glb_models_df)[, dsp_models_cols])## id max.Accuracy.OOB max.Kappa.OOB
## 4 Max.cor.Y##rcv#rpart 0.7276701 0.4783438508
## 5 All.X##rcv#glmnet 0.7229115 0.4729121383
## 3 Max.cor.Y.rcv.1X1###glmnet 0.6859711 0.3481272164
## 1 MFO###myMFO_classfr 0.5850546 0.0000000000
## 2 Random###myrandom_classfr 0.3991540 0.0006568311# print(myplot_radar(radar_inp_df = dsp_models_df))
print("Metrics used for model selection:"); print(get_model_sel_frmla())## [1] "Metrics used for model selection:"## ~-max.Accuracy.OOB - max.Kappa.OOB
## <environment: 0x7fc5577bbc28>print(sprintf("Best model id: %s", dsp_models_df[1, "id"]))## [1] "Best model id: Max.cor.Y##rcv#rpart"glb_get_predictions <- function(df, mdl_id, rsp_var, prob_threshold_def=NULL, verbose=FALSE) {
mdl <- glb_models_lst[[mdl_id]]
clmnNames <- mygetPredictIds(rsp_var, mdl_id)
predct_var_name <- clmnNames$value
predct_prob_var_name <- clmnNames$prob
predct_accurate_var_name <- clmnNames$is.acc
predct_error_var_name <- clmnNames$err
predct_erabs_var_name <- clmnNames$err.abs
if (glb_is_regression) {
df[, predct_var_name] <- predict(mdl, newdata=df, type="raw")
if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_var_name) +
facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="glm"))
df[, predct_error_var_name] <- df[, predct_var_name] - df[, glb_rsp_var]
if (verbose) print(myplot_scatter(df, predct_var_name, predct_error_var_name) +
#facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="auto"))
if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_error_var_name) +
#facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
stat_smooth(method="glm"))
df[, predct_erabs_var_name] <- abs(df[, predct_error_var_name])
if (verbose) print(head(orderBy(reformulate(c("-", predct_erabs_var_name)), df)))
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
if (glb_is_classification && glb_is_binomial) {
prob_threshold <- glb_models_df[glb_models_df$id == mdl_id,
"opt.prob.threshold.OOB"]
if (is.null(prob_threshold) || is.na(prob_threshold)) {
warning("Using default probability threshold: ", prob_threshold_def)
if (is.null(prob_threshold <- prob_threshold_def))
stop("Default probability threshold is NULL")
}
df[, predct_prob_var_name] <- predict(mdl, newdata = df, type = "prob")[, 2]
df[, predct_var_name] <-
factor(levels(df[, glb_rsp_var])[
(df[, predct_prob_var_name] >=
prob_threshold) * 1 + 1], levels(df[, glb_rsp_var]))
# if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_var_name) +
# facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="glm"))
df[, predct_error_var_name] <- df[, predct_var_name] != df[, glb_rsp_var]
# if (verbose) print(myplot_scatter(df, predct_var_name, predct_error_var_name) +
# #facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="auto"))
# if (verbose) print(myplot_scatter(df, glb_rsp_var, predct_error_var_name) +
# #facet_wrap(reformulate(glbFeatsCategory), scales = "free") +
# stat_smooth(method="glm"))
# if prediction is a TP (true +ve), measure distance from 1.0
tp <- which((df[, predct_var_name] == df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[2]))
df[tp, predct_erabs_var_name] <- abs(1 - df[tp, predct_prob_var_name])
#rowIx <- which.max(df[tp, predct_erabs_var_name]); df[tp, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a TN (true -ve), measure distance from 0.0
tn <- which((df[, predct_var_name] == df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[1]))
df[tn, predct_erabs_var_name] <- abs(0 - df[tn, predct_prob_var_name])
#rowIx <- which.max(df[tn, predct_erabs_var_name]); df[tn, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a FP (flse +ve), measure distance from 0.0
fp <- which((df[, predct_var_name] != df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[2]))
df[fp, predct_erabs_var_name] <- abs(0 - df[fp, predct_prob_var_name])
#rowIx <- which.max(df[fp, predct_erabs_var_name]); df[fp, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
# if prediction is a FN (flse -ve), measure distance from 1.0
fn <- which((df[, predct_var_name] != df[, glb_rsp_var]) &
(df[, predct_var_name] == levels(df[, glb_rsp_var])[1]))
df[fn, predct_erabs_var_name] <- abs(1 - df[fn, predct_prob_var_name])
#rowIx <- which.max(df[fn, predct_erabs_var_name]); df[fn, c(glbFeatsId, glb_rsp_var, predct_var_name, predct_prob_var_name, predct_erabs_var_name)][rowIx, ]
if (verbose) print(head(orderBy(reformulate(c("-", predct_erabs_var_name)), df)))
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
if (glb_is_classification && !glb_is_binomial) {
df[, predct_var_name] <- predict(mdl, newdata = df, type = "raw")
probCls <- predict(mdl, newdata = df, type = "prob")
df[, predct_prob_var_name] <- NA
for (cls in names(probCls)) {
mask <- (df[, predct_var_name] == cls)
df[mask, predct_prob_var_name] <- probCls[mask, cls]
}
if (verbose) print(myplot_histogram(df, predct_prob_var_name,
fill_col_name = predct_var_name))
if (verbose) print(myplot_histogram(df, predct_prob_var_name,
facet_frmla = paste0("~", glb_rsp_var)))
# if prediction is erroneous, measure predicted class prob from actual class prob
if (all(is.na(df[, glb_rsp_var]))) {
df[, predct_error_var_name] <- NA
df[, predct_erabs_var_name] <- NA
df[, predct_accurate_var_name] <- NA
} else {
df[, predct_error_var_name] <- df[, predct_var_name] != df[, glb_rsp_var]
df[, predct_erabs_var_name] <- 0
for (cls in names(probCls)) {
mask <- (df[, glb_rsp_var] == cls) & (df[, predct_error_var_name])
df[mask, predct_erabs_var_name] <- probCls[mask, cls]
}
df[, predct_accurate_var_name] <- (df[, glb_rsp_var] == df[, predct_var_name])
}
}
return(df)
}
#stop(here"); glb2Sav(); glbObsAll <- savObsAll; glbObsTrn <- savObsTrn; glbObsFit <- savObsFit; glbObsOOB <- savObsOOB; sav_models_df <- glb_models_df; glb_models_df <- sav_models_df; glb_featsimp_df <- sav_featsimp_df
myget_category_stats <- function(obs_df, mdl_id, label) {
require(dplyr)
require(lazyeval)
predct_var_name <- mygetPredictIds(glb_rsp_var, mdl_id)$value
predct_error_var_name <- mygetPredictIds(glb_rsp_var, mdl_id)$err.abs
if (!predct_var_name %in% names(obs_df))
obs_df <- glb_get_predictions(obs_df, mdl_id, glb_rsp_var)
tmp_obs_df <- obs_df[, c(glbFeatsCategory, glb_rsp_var,
predct_var_name, predct_error_var_name)]
# tmp_obs_df <- obs_df %>%
# dplyr::select_(glbFeatsCategory, glb_rsp_var, predct_var_name, predct_error_var_name)
#dplyr::rename(startprice.log10.predict.RFE.X.glmnet.err=error_abs_OOB)
names(tmp_obs_df)[length(names(tmp_obs_df))] <- paste0("err.abs.", label)
ret_ctgry_df <- tmp_obs_df %>%
dplyr::group_by_(glbFeatsCategory) %>%
dplyr::summarise_(#interp(~sum(abs(var)), var=as.name(glb_rsp_var)),
interp(~sum(var), var=as.name(paste0("err.abs.", label))),
interp(~mean(var), var=as.name(paste0("err.abs.", label))),
interp(~n()))
names(ret_ctgry_df) <- c(glbFeatsCategory,
#paste0(glb_rsp_var, ".abs.", label, ".sum"),
paste0("err.abs.", label, ".sum"),
paste0("err.abs.", label, ".mean"),
paste0(".n.", label))
ret_ctgry_df <- dplyr::ungroup(ret_ctgry_df)
#colSums(ret_ctgry_df[, -grep(glbFeatsCategory, names(ret_ctgry_df))])
return(ret_ctgry_df)
}
#print(colSums((ctgry_df <- myget_category_stats(obs_df=glbObsFit, mdl_id="", label="fit"))[, -grep(glbFeatsCategory, names(ctgry_df))]))
if (!is.null(glb_mdl_ensemble)) {
fit.models_2_chunk_df <- myadd_chunk(fit.models_2_chunk_df,
paste0("fit.models_2_", mdl_id_pfx), major.inc = TRUE,
label.minor = "ensemble")
mdl_id_pfx <- "Ensemble"
if (#(glb_is_regression) |
((glb_is_classification) & (!glb_is_binomial)))
stop("Ensemble models not implemented yet for multinomial classification")
mygetEnsembleAutoMdlIds <- function() {
tmp_models_df <- orderBy(get_model_sel_frmla(), glb_models_df)
row.names(tmp_models_df) <- tmp_models_df$id
mdl_threshold_pos <-
min(which(grepl("MFO|Random|Baseline", tmp_models_df$id))) - 1
mdlIds <- tmp_models_df$id[1:mdl_threshold_pos]
return(mdlIds[!grepl("Ensemble", mdlIds)])
}
if (glb_mdl_ensemble == "auto") {
glb_mdl_ensemble <- mygetEnsembleAutoMdlIds()
mdl_id_pfx <- paste0(mdl_id_pfx, ".auto")
} else if (grepl("^%<d-%", glb_mdl_ensemble)) {
glb_mdl_ensemble <- eval(parse(text =
str_trim(unlist(strsplit(glb_mdl_ensemble, "%<d-%"))[2])))
}
for (mdl_id in glb_mdl_ensemble) {
if (!(mdl_id %in% names(glb_models_lst))) {
warning("Model ", mdl_id, " in glb_model_ensemble not found !")
next
}
glbObsFit <- glb_get_predictions(df = glbObsFit, mdl_id, glb_rsp_var)
glbObsOOB <- glb_get_predictions(df = glbObsOOB, mdl_id, glb_rsp_var)
}
#mdl_id_pfx <- "Ensemble.RFE"; mdlId <- paste0(mdl_id_pfx, ".glmnet")
#glb_mdl_ensemble <- gsub(mygetPredictIds$value, "", grep("RFE\\.X\\.(?!Interact)", row.names(glb_featsimp_df), perl = TRUE, value = TRUE), fixed = TRUE)
#varImp(glb_models_lst[[mdlId]])
#cor_df <- data.frame(cor=cor(glbObsFit[, glb_rsp_var], glbObsFit[, paste(mygetPredictIds$value, glb_mdl_ensemble)], use="pairwise.complete.obs"))
#glbObsFit <- glb_get_predictions(df=glbObsFit, "Ensemble.glmnet", glb_rsp_var);print(colSums((ctgry_df <- myget_category_stats(obs_df=glbObsFit, mdl_id="Ensemble.glmnet", label="fit"))[, -grep(glbFeatsCategory, names(ctgry_df))]))
### bid0_sp
# Better than MFO; models.n=28; min.RMSE.fit=0.0521233; err.abs.fit.sum=7.3631895
# old: Top x from auto; models.n= 5; min.RMSE.fit=0.06311047; err.abs.fit.sum=9.5937080
# RFE only ; models.n=16; min.RMSE.fit=0.05148588; err.abs.fit.sum=7.2875091
# RFE subset only ;models.n= 5; min.RMSE.fit=0.06040702; err.abs.fit.sum=9.059088
# RFE subset only ;models.n= 9; min.RMSE.fit=0.05933167; err.abs.fit.sum=8.7421288
# RFE subset only ;models.n=15; min.RMSE.fit=0.0584607; err.abs.fit.sum=8.5902066
# RFE subset only ;models.n=17; min.RMSE.fit=0.05496899; err.abs.fit.sum=8.0170431
# RFE subset only ;models.n=18; min.RMSE.fit=0.05441577; err.abs.fit.sum=7.837223
# RFE subset only ;models.n=16; min.RMSE.fit=0.05441577; err.abs.fit.sum=7.837223
### bid0_sp
### bid1_sp
# "auto"; err.abs.fit.sum=76.699774; min.RMSE.fit=0.2186429
# "RFE.X.*"; err.abs.fit.sum=; min.RMSE.fit=0.221114
### bid1_sp
indepVar <- paste(mygetPredictIds(glb_rsp_var)$value, glb_mdl_ensemble, sep = "")
if (glb_is_classification)
indepVar <- paste(indepVar, ".prob", sep = "")
# Some models in glb_mdl_ensemble might not be fitted e.g. RFE.X.Interact
indepVar <- intersect(indepVar, names(glbObsFit))
# indepVar <- grep(mygetPredictIds(glb_rsp_var)$value, names(glbObsFit), fixed=TRUE, value=TRUE)
# if (glb_is_regression)
# indepVar <- indepVar[!grepl("(err\\.abs|accurate)$", indepVar)]
# if (glb_is_classification && glb_is_binomial)
# indepVar <- grep("prob$", indepVar, value=TRUE) else
# indepVar <- indepVar[!grepl("err$", indepVar)]
#rfe_fit_ens_results <- myrun_rfe(glbObsFit, indepVar)
for (method in c("glm", "glmnet")) {
for (trainControlMethod in
c("boot", "boot632", "cv", "repeatedcv"
#, "LOOCV" # tuneLength * nrow(fitDF)
, "LGOCV", "adaptive_cv"
#, "adaptive_boot" #error: adaptive$min should be less than 3
#, "adaptive_LGOCV" #error: adaptive$min should be less than 3
)) {
#sav_models_df <- glb_models_df; all.equal(sav_models_df, glb_models_df)
#glb_models_df <- sav_models_df; print(glb_models_df$id)
if ((method == "glm") && (trainControlMethod != "repeatedcv"))
# glm used only to identify outliers
next
ret_lst <- myfit_mdl(
mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = paste0(mdl_id_pfx, ".", trainControlMethod),
type = glb_model_type, tune.df = NULL,
trainControl.method = trainControlMethod,
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = method)),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = glbObsFit, OOB_df = glbObsOOB)
}
}
dsp_models_df <- get_dsp_models_df()
}
if (is.null(glb_sel_mdl_id))
glb_sel_mdl_id <- dsp_models_df[1, "id"] else
print(sprintf("User specified selection: %s", glb_sel_mdl_id)) ## [1] "User specified selection: All.X##rcv#glmnet"myprint_mdl(glb_sel_mdl <- glb_models_lst[[glb_sel_mdl_id]])
## Length Class Mode
## a0 380 -none- numeric
## beta 5 -none- list
## dfmat 380 -none- numeric
## df 76 -none- numeric
## dim 2 -none- numeric
## lambda 76 -none- numeric
## dev.ratio 76 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 5 -none- character
## grouped 1 -none- logical
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 28 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 5 -none- character
## [1] "min lambda > lambdaOpt:"
## [1] "class: Disabled:"
##
## -0.682133676
## .rnorm
## 0.016236821
## Age
## 0.052704231
## Citizenship.fctrCitizen, Naturalized
## -0.505511515
## Citizenship.fctrNon-Citizen
## -0.860459043
## Education.fctrBachelor's degree
## -0.629820356
## Education.fctrDoctorate degree
## -0.626569025
## Education.fctrHigh school
## 0.362734617
## Education.fctrMaster's degree
## -0.868888624
## Education.fctrNo high school diploma
## 1.064677342
## Education.fctrProfessional degree
## -0.757369329
## Education.fctrSome college, no degree
## 0.115647622
## Married.fctrMarried
## -0.857965891
## Married.fctrSeparated
## 0.160275744
## PeopleInHousehold
## -0.016579180
## Race.fctrAmerican Indian
## 0.009019554
## Race.fctrAsian
## -0.072868661
## Race.fctrBlack
## 0.310408699
## Race.fctrMultiracial
## 0.092364638
## Race.fctrPacific Islander
## 0.275381398
## Region.fctrMidwest
## -0.071696043
## Region.fctrNortheast
## -0.016321483
## Region.fctrWest
## -0.105253659
## [1] "class: Employed:"
##
## 4.07376570
## .rnorm
## 0.01129780
## Citizenship.fctrCitizen, Naturalized
## 0.08291596
## Citizenship.fctrNon-Citizen
## 0.07695471
## Education.fctrBachelor's degree
## 0.15279080
## Education.fctrDoctorate degree
## 0.76855035
## Education.fctrHigh school
## -0.45606953
## Education.fctrMaster's degree
## 0.25793173
## Education.fctrNo high school diploma
## -0.85274987
## Education.fctrProfessional degree
## 0.53560074
## Education.fctrSome college, no degree
## -0.21721324
## Hispanic
## 0.05415627
## Married.fctrNever Married
## -0.20637501
## Married.fctrWidowed
## -0.11773377
## Race.fctrAmerican Indian
## -0.36911791
## Race.fctrBlack
## -0.20263429
## Race.fctrMultiracial
## -0.12817419
## Race.fctrPacific Islander
## -0.15995753
## Region.fctrMidwest
## 0.14673165
## Region.fctrNortheast
## 0.08782864
## Sex.fctrMale
## 0.22191720
## [1] "class: Not.in.Labor.Force:"
##
## 3.24612651
## Age
## -0.04130075
## Citizenship.fctrCitizen, Naturalized
## 0.04137445
## Citizenship.fctrNon-Citizen
## 0.15887442
## Education.fctrMaster's degree
## -0.04074203
## Education.fctrNo high school diploma
## 0.96791390
## Education.fctrSome college, no degree
## 0.23005093
## Hispanic
## -0.10370630
## Married.fctrMarried
## 0.25953648
## Married.fctrNever Married
## 0.33375203
## Married.fctrSeparated
## -0.03752998
## Married.fctrWidowed
## 0.58309739
## PeopleInHousehold
## 0.14682379
## Race.fctrAsian
## 0.43940282
## Race.fctrBlack
## -0.09106900
## Race.fctrMultiracial
## 0.05427560
## Region.fctrMidwest
## -0.14995281
## Sex.fctrMale
## -0.71644104
## [1] "class: Retired:"
## .rnorm
## -7.766237327 -0.016588779
## Age Citizenship.fctrCitizen, Naturalized
## 0.180449160 -0.210603156
## Citizenship.fctrNon-Citizen Education.fctrBachelor's degree
## -0.291485719 0.041172954
## Education.fctrDoctorate degree Education.fctrHigh school
## 0.034833709 -0.076053875
## Education.fctrMaster's degree Married.fctrMarried
## 0.235914499 0.408448441
## Married.fctrNever Married Married.fctrSeparated
## -0.049324597 -0.215449376
## Married.fctrWidowed PeopleInHousehold
## 0.527580786 -0.159180446
## Race.fctrAmerican Indian Race.fctrAsian
## -0.180429213 0.149154928
## Race.fctrMultiracial Race.fctrPacific Islander
## -0.112375180 -0.184683057
## Region.fctrNortheast Region.fctrWest
## -0.001068302 0.080242502
## Sex.fctrMale
## -0.112094049
## [1] "class: Unemployed:"
##
## 1.128478797
## Age
## -0.003594189
## Education.fctrHigh school
## 0.006293782
## Education.fctrNo high school diploma
## -0.117670195
## Education.fctrSome college, no degree
## -0.003394560
## Hispanic
## 0.171124677
## Married.fctrMarried
## -0.539803262
## Married.fctrNever Married
## 0.026250406
## Married.fctrSeparated
## 0.056433648
## Married.fctrWidowed
## -0.113801986
## PeopleInHousehold
## 0.071712840
## Race.fctrAmerican Indian
## 0.226698090
## Race.fctrAsian
## -0.055242748
## Race.fctrBlack
## 0.499911437
## Race.fctrPacific Islander
## 0.027777413
## Region.fctrMidwest
## 0.034678764
## Region.fctrNortheast
## 0.151019068
## Region.fctrWest
## 0.091052386
## Sex.fctrMale
## 0.229847065
## [1] "max lambda < lambdaOpt:"
## [1] "Feats mismatch between coefs_left & rght:"
## [1] ""
## [2] ".rnorm"
## [3] "Age"
## [4] "Citizenship.fctrCitizen, Naturalized"
## [5] "Citizenship.fctrNon-Citizen"
## [6] "Education.fctrBachelor's degree"
## [7] "Education.fctrDoctorate degree"
## [8] "Education.fctrHigh school"
## [9] "Education.fctrMaster's degree"
## [10] "Education.fctrNA.my"
## [11] "Education.fctrNo high school diploma"
## [12] "Education.fctrProfessional degree"
## [13] "Education.fctrSome college, no degree"
## [14] "Hispanic"
## [15] "Married.fctrMarried"
## [16] "Married.fctrNA.my"
## [17] "Married.fctrNever Married"
## [18] "Married.fctrSeparated"
## [19] "Married.fctrWidowed"
## [20] "PeopleInHousehold"
## [21] "Race.fctrAmerican Indian"
## [22] "Race.fctrAsian"
## [23] "Race.fctrBlack"
## [24] "Race.fctrMultiracial"
## [25] "Race.fctrPacific Islander"
## [26] "Region.fctrMidwest"
## [27] "Region.fctrNortheast"
## [28] "Region.fctrWest"
## [29] "Sex.fctrMale"## [1] TRUE# From here to save(), this should all be in one function
# these are executed in the same seq twice more:
# fit.data.training & predict.data.new chunks
print(sprintf("%s fit prediction diagnostics:", glb_sel_mdl_id))## [1] "All.X##rcv#glmnet fit prediction diagnostics:"glbObsFit <- glb_get_predictions(df = glbObsFit, mdl_id = glb_sel_mdl_id,
rsp_var = glb_rsp_var)
print(sprintf("%s OOB prediction diagnostics:", glb_sel_mdl_id))## [1] "All.X##rcv#glmnet OOB prediction diagnostics:"glbObsOOB <- glb_get_predictions(df = glbObsOOB, mdl_id = glb_sel_mdl_id,
rsp_var = glb_rsp_var)
print(glb_featsimp_df <- myget_feats_importance(mdl = glb_sel_mdl, featsimp_df = NULL))## All.X..rcv.glmnet.imp.Disabled
## .rnorm 1.5250461
## Age 4.9502539
## Citizenship.fctrCitizen, Naturalized 47.4802548
## Citizenship.fctrNon-Citizen 80.8187616
## Education.fctrBachelor's degree 59.1559838
## Education.fctrDoctorate degree 58.8506019
## Education.fctrHigh school 34.0699104
## Education.fctrMaster's degree 81.6105115
## Education.fctrNA.my 0.0000000
## Education.fctrNo high school diploma 100.0000000
## Education.fctrProfessional degree 71.1360427
## Education.fctrSome college, no degree 10.8622226
## Hispanic 0.0000000
## Married.fctrMarried 80.5845919
## Married.fctrNA.my 0.0000000
## Married.fctrNever Married 0.0000000
## Married.fctrSeparated 15.0539265
## Married.fctrWidowed 0.0000000
## PeopleInHousehold 1.5572023
## Race.fctrAmerican Indian 0.8471631
## Race.fctrAsian 6.8442014
## Race.fctrBlack 29.1551897
## Race.fctrMultiracial 8.6753643
## Race.fctrPacific Islander 25.8652446
## Region.fctrMidwest 6.7340630
## Region.fctrNortheast 1.5329980
## Region.fctrWest 9.8859677
## Sex.fctrMale 0.0000000
## All.X..rcv.glmnet.imp.Employed
## .rnorm 1.061148
## Age 0.000000
## Citizenship.fctrCitizen, Naturalized 7.787895
## Citizenship.fctrNon-Citizen 7.227984
## Education.fctrBachelor's degree 14.350902
## Education.fctrDoctorate degree 72.186222
## Education.fctrHigh school 42.836408
## Education.fctrMaster's degree 24.226282
## Education.fctrNA.my 0.000000
## Education.fctrNo high school diploma 80.094677
## Education.fctrProfessional degree 50.306390
## Education.fctrSome college, no degree 20.401790
## Hispanic 5.086637
## Married.fctrMarried 0.000000
## Married.fctrNA.my 0.000000
## Married.fctrNever Married 19.383808
## Married.fctrSeparated 0.000000
## Married.fctrWidowed 11.058165
## PeopleInHousehold 0.000000
## Race.fctrAmerican Indian 34.669462
## Race.fctrAsian 0.000000
## Race.fctrBlack 19.032460
## Race.fctrMultiracial 12.038783
## Race.fctrPacific Islander 15.024038
## Region.fctrMidwest 13.781795
## Region.fctrNortheast 8.249320
## Region.fctrWest 0.000000
## Sex.fctrMale 20.843611
## All.X..rcv.glmnet.imp.Not.in.Labor.Force
## .rnorm 0.000000
## Age 3.879180
## Citizenship.fctrCitizen, Naturalized 3.886102
## Citizenship.fctrNon-Citizen 14.922307
## Education.fctrBachelor's degree 0.000000
## Education.fctrDoctorate degree 0.000000
## Education.fctrHigh school 0.000000
## Education.fctrMaster's degree 3.826702
## Education.fctrNA.my 0.000000
## Education.fctrNo high school diploma 90.911477
## Education.fctrProfessional degree 0.000000
## Education.fctrSome college, no degree 21.607572
## Hispanic 9.740632
## Married.fctrMarried 24.377008
## Married.fctrNA.my 0.000000
## Married.fctrNever Married 31.347716
## Married.fctrSeparated 3.525010
## Married.fctrWidowed 54.767522
## PeopleInHousehold 13.790449
## Race.fctrAmerican Indian 0.000000
## Race.fctrAsian 41.270984
## Race.fctrBlack 8.553671
## Race.fctrMultiracial 5.097845
## Race.fctrPacific Islander 0.000000
## Region.fctrMidwest 14.084344
## Region.fctrNortheast 0.000000
## Region.fctrWest 0.000000
## Sex.fctrMale 67.291846
## All.X..rcv.glmnet.imp.Retired
## .rnorm 1.5581039
## Age 16.9487180
## Citizenship.fctrCitizen, Naturalized 19.7809372
## Citizenship.fctrNon-Citizen 27.3778456
## Education.fctrBachelor's degree 3.8671767
## Education.fctrDoctorate degree 3.2717620
## Education.fctrHigh school 7.1433732
## Education.fctrMaster's degree 22.1583093
## Education.fctrNA.my 0.0000000
## Education.fctrNo high school diploma 0.0000000
## Education.fctrProfessional degree 0.0000000
## Education.fctrSome college, no degree 0.0000000
## Hispanic 0.0000000
## Married.fctrMarried 38.3635891
## Married.fctrNA.my 0.0000000
## Married.fctrNever Married 4.6328211
## Married.fctrSeparated 20.2361192
## Married.fctrWidowed 49.5531148
## PeopleInHousehold 14.9510504
## Race.fctrAmerican Indian 16.9468444
## Race.fctrAsian 14.0094019
## Race.fctrBlack 0.0000000
## Race.fctrMultiracial 10.5548579
## Race.fctrPacific Islander 17.3463875
## Region.fctrMidwest 0.0000000
## Region.fctrNortheast 0.1003404
## Region.fctrWest 7.5367906
## Sex.fctrMale 10.5284526
## All.X..rcv.glmnet.imp.Unemployed imp
## .rnorm 0.0000000 -1
## Age 0.3375848 -2
## Citizenship.fctrCitizen, Naturalized 0.0000000 -3
## Citizenship.fctrNon-Citizen 0.0000000 -4
## Education.fctrBachelor's degree 0.0000000 -5
## Education.fctrDoctorate degree 0.0000000 -6
## Education.fctrHigh school 0.5911445 -7
## Education.fctrMaster's degree 0.0000000 -8
## Education.fctrNA.my 0.0000000 -9
## Education.fctrNo high school diploma 11.0521930 -10
## Education.fctrProfessional degree 0.0000000 -11
## Education.fctrSome college, no degree 0.3188346 -12
## Hispanic 16.0729143 -13
## Married.fctrMarried 50.7011130 -14
## Married.fctrNA.my 0.0000000 -15
## Married.fctrNever Married 2.4655739 -16
## Married.fctrSeparated 5.3005399 -17
## Married.fctrWidowed 10.6888708 -18
## PeopleInHousehold 6.7356407 -19
## Race.fctrAmerican Indian 21.2926566 -20
## Race.fctrAsian 5.1886845 -21
## Race.fctrBlack 46.9542665 -22
## Race.fctrMultiracial 0.0000000 -23
## Race.fctrPacific Islander 2.6089982 -24
## Region.fctrMidwest 3.2572087 -25
## Region.fctrNortheast 14.1844916 -26
## Region.fctrWest 8.5521108 -27
## Sex.fctrMale 21.5884246 -28#mdl_id <-"RFE.X.glmnet"; glb_featsimp_df <- myget_feats_importance(glb_models_lst[[mdl_id]], glb_featsimp_df); glb_featsimp_df[, paste0(mdl_id, ".imp")] <- glb_featsimp_df$imp; print(glb_featsimp_df)
#print(head(sbst_featsimp_df <- subset(glb_featsimp_df, is.na(RFE.X.glmnet.imp) | (abs(RFE.X.YeoJohnson.glmnet.imp - RFE.X.glmnet.imp) > 0.0001), select=-imp)))
#print(orderBy(~ -cor.y.abs, subset(glb_feats_df, id %in% c(row.names(sbst_featsimp_df), "startprice.dcm1.is9", "D.weight.post.stop.sum"))))
# Used again in fit.data.training & predict.data.new chunks
glb_analytics_diag_plots <- function(obs_df, mdl_id, prob_threshold=NULL) {
if (!is.null(featsimp_df <- glb_featsimp_df)) {
featsimp_df$feat <- gsub("`(.*?)`", "\\1", row.names(featsimp_df))
featsimp_df$feat.interact <- gsub("(.*?):(.*)", "\\2", featsimp_df$feat)
featsimp_df$feat <- gsub("(.*?):(.*)", "\\1", featsimp_df$feat)
featsimp_df$feat.interact <-
ifelse(featsimp_df$feat.interact == featsimp_df$feat,
NA, featsimp_df$feat.interact)
featsimp_df$feat <-
gsub("(.*?)\\.fctr(.*)", "\\1\\.fctr", featsimp_df$feat)
featsimp_df$feat.interact <-
gsub("(.*?)\\.fctr(.*)", "\\1\\.fctr", featsimp_df$feat.interact)
featsimp_df <- orderBy(~ -imp.max,
summaryBy(imp ~ feat + feat.interact, data=featsimp_df,
FUN=max))
#rex_str=":(.*)"; txt_vctr=tail(featsimp_df$feat); ret_lst <- regexec(rex_str, txt_vctr); ret_lst <- regmatches(txt_vctr, ret_lst); ret_vctr <- sapply(1:length(ret_lst), function(pos_ix) ifelse(length(ret_lst[[pos_ix]]) > 0, ret_lst[[pos_ix]], "")); print(ret_vctr <- ret_vctr[ret_vctr != ""])
featsimp_df <- subset(featsimp_df, !is.na(imp.max))
if (nrow(featsimp_df) > 5) {
warning("Limiting important feature scatter plots to 5 out of ",
nrow(featsimp_df))
featsimp_df <- head(featsimp_df, 5)
}
# if (!all(is.na(featsimp_df$feat.interact)))
# stop("not implemented yet")
rsp_var_out <- mygetPredictIds(glb_rsp_var, mdl_id)$value
for (var in featsimp_df$feat) {
plot_df <- melt(obs_df, id.vars = var,
measure.vars = c(glb_rsp_var, rsp_var_out))
print(myplot_scatter(plot_df, var, "value", colorcol_name = "variable",
facet_colcol_name = "variable", jitter = TRUE) +
guides(color = FALSE))
}
}
if (glb_is_regression) {
if (is.null(featsimp_df) || (nrow(featsimp_df) == 0))
warning("No important features in glb_fin_mdl") else
print(myplot_prediction_regression(df=obs_df,
feat_x=ifelse(nrow(featsimp_df) > 1, featsimp_df$feat[2],
".rownames"),
feat_y=featsimp_df$feat[1],
rsp_var=glb_rsp_var, rsp_var_out=rsp_var_out,
id_vars=glbFeatsId)
# + facet_wrap(reformulate(featsimp_df$feat[2])) # if [1 or 2] is a factor
# + geom_point(aes_string(color="<col_name>.fctr")) # to color the plot
)
}
if (glb_is_classification) {
if (is.null(featsimp_df) || (nrow(featsimp_df) == 0))
warning("No features in selected model are statistically important")
else print(myplot_prediction_classification(df = obs_df,
feat_x = ifelse(nrow(featsimp_df) > 1,
featsimp_df$feat[2], ".rownames"),
feat_y = featsimp_df$feat[1],
rsp_var = glb_rsp_var,
rsp_var_out = rsp_var_out,
id_vars = glbFeatsId,
prob_threshold = prob_threshold))
}
}
if (glb_is_classification && glb_is_binomial)
glb_analytics_diag_plots(obs_df = glbObsOOB, mdl_id = glb_sel_mdl_id,
prob_threshold = glb_models_df[glb_models_df$id == glb_sel_mdl_id,
"opt.prob.threshold.OOB"]) else
glb_analytics_diag_plots(obs_df = glbObsOOB, mdl_id = glb_sel_mdl_id) ## Warning in glb_analytics_diag_plots(obs_df = glbObsOOB, mdl_id =
## glb_sel_mdl_id): Limiting important feature scatter plots to 5 out of 10
## [1] "Min/Max Boundaries: "
## .rownames EmploymentStatus.fctr EmploymentStatus.fctr.All.X..rcv.glmnet
## 1 82324 Employed Employed
## 2 61899 Disabled Retired
## 3 5444 Disabled Retired
## 4 67205 Disabled Retired
## 5 11233 Disabled Retired
## 6 116110 Disabled Retired
## 7 123652 Not.in.Labor.Force Retired
## 8 55065 Disabled Retired
## 9 72295 Disabled Not.in.Labor.Force
## 10 57730 Disabled Not.in.Labor.Force
## 11 57728 Disabled Not.in.Labor.Force
## 12 32062 Disabled Employed
## 13 29898 Disabled Not.in.Labor.Force
## 14 11138 Disabled Not.in.Labor.Force
## EmploymentStatus.fctr.All.X..rcv.glmnet.prob
## 1 0.7778538
## 2 0.9556859
## 3 0.9503372
## 4 0.9470713
## 5 0.9432245
## 6 0.8885648
## 7 0.8851479
## 8 0.8369017
## 9 0.7046648
## 10 0.7007226
## 11 0.7001114
## 12 0.6627180
## 13 0.5393194
## 14 0.5362889
## EmploymentStatus.fctr.All.X..rcv.glmnet.err
## 1 FALSE
## 2 TRUE
## 3 TRUE
## 4 TRUE
## 5 TRUE
## 6 TRUE
## 7 TRUE
## 8 TRUE
## 9 TRUE
## 10 TRUE
## 11 TRUE
## 12 TRUE
## 13 TRUE
## 14 TRUE
## EmploymentStatus.fctr.All.X..rcv.glmnet.err.abs
## 1 0.000000000
## 2 0.013422721
## 3 0.040495037
## 4 0.043283137
## 5 0.025951125
## 6 0.094001537
## 7 0.008501801
## 8 0.139822440
## 9 0.019134060
## 10 0.024769281
## 11 0.024868089
## 12 0.019493680
## 13 0.039002030
## 14 0.039547328
## EmploymentStatus.fctr.All.X..rcv.glmnet.is.acc
## 1 TRUE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## 7 FALSE
## 8 FALSE
## 9 FALSE
## 10 FALSE
## 11 FALSE
## 12 FALSE
## 13 FALSE
## 14 FALSE
## EmploymentStatus.fctr.All.X..rcv.glmnet.accurate
## 1 TRUE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## 7 FALSE
## 8 FALSE
## 9 FALSE
## 10 FALSE
## 11 FALSE
## 12 FALSE
## 13 FALSE
## 14 FALSE
## EmploymentStatus.fctr.All.X..rcv.glmnet.error .label
## 1 0.00000000 82324
## 2 0.04431409 61899
## 3 0.04966279 5444
## 4 0.05292870 67205
## 5 0.05677555 11233
## 6 0.11143520 116110
## 7 0.11485210 123652
## 8 0.16309828 55065
## 9 0.29533517 72295
## 10 0.29927742 57730
## 11 0.29988859 57728
## 12 0.33728198 32062
## 13 0.46068055 29898
## 14 0.46371111 11138
## [1] "Inaccurate: "
## .rownames EmploymentStatus.fctr EmploymentStatus.fctr.All.X..rcv.glmnet
## 1 30168 Employed Retired
## 2 74437 Disabled Retired
## 3 26711 Employed Retired
## 4 65338 Employed Retired
## 5 18966 Employed Retired
## 6 35251 Employed Retired
## EmploymentStatus.fctr.All.X..rcv.glmnet.prob
## 1 0.9717483
## 2 0.9710020
## 3 0.9704153
## 4 0.9686106
## 5 0.9683116
## 6 0.9681395
## EmploymentStatus.fctr.All.X..rcv.glmnet.err
## 1 TRUE
## 2 TRUE
## 3 TRUE
## 4 TRUE
## 5 TRUE
## 6 TRUE
## EmploymentStatus.fctr.All.X..rcv.glmnet.err.abs
## 1 0.01580123
## 2 0.01416346
## 3 0.01279953
## 4 0.02308573
## 5 0.01119513
## 6 0.01574859
## EmploymentStatus.fctr.All.X..rcv.glmnet.is.acc
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## EmploymentStatus.fctr.All.X..rcv.glmnet.accurate
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## EmploymentStatus.fctr.All.X..rcv.glmnet.error
## 1 0.02825168
## 2 0.02899799
## 3 0.02958467
## 4 0.03138936
## 5 0.03168842
## 6 0.03186054
## .rownames EmploymentStatus.fctr
## 1072 98956 Not.in.Labor.Force
## 1321 15491 Not.in.Labor.Force
## 3129 41018 Retired
## 3657 82571 Not.in.Labor.Force
## 3930 4221 Not.in.Labor.Force
## 6261 17235 Retired
## EmploymentStatus.fctr.All.X..rcv.glmnet
## 1072 Employed
## 1321 Employed
## 3129 Employed
## 3657 Employed
## 3930 Employed
## 6261 Employed
## EmploymentStatus.fctr.All.X..rcv.glmnet.prob
## 1072 0.8049305
## 1321 0.7875132
## 3129 0.6858792
## 3657 0.6579430
## 3930 0.6435715
## 6261 0.5049103
## EmploymentStatus.fctr.All.X..rcv.glmnet.err
## 1072 TRUE
## 1321 TRUE
## 3129 TRUE
## 3657 TRUE
## 3930 TRUE
## 6261 TRUE
## EmploymentStatus.fctr.All.X..rcv.glmnet.err.abs
## 1072 0.1642977
## 1321 0.1623444
## 3129 0.2503397
## 3657 0.2875168
## 3930 0.2147354
## 6261 0.4440958
## EmploymentStatus.fctr.All.X..rcv.glmnet.is.acc
## 1072 FALSE
## 1321 FALSE
## 3129 FALSE
## 3657 FALSE
## 3930 FALSE
## 6261 FALSE
## EmploymentStatus.fctr.All.X..rcv.glmnet.accurate
## 1072 FALSE
## 1321 FALSE
## 3129 FALSE
## 3657 FALSE
## 3930 FALSE
## 6261 FALSE
## EmploymentStatus.fctr.All.X..rcv.glmnet.error
## 1072 0.1950695
## 1321 0.2124868
## 3129 0.3141208
## 3657 0.3420570
## 3930 0.3564285
## 6261 0.4950897
## .rownames EmploymentStatus.fctr
## 7856 82366 Disabled
## 7857 31285 Unemployed
## 7858 103225 Employed
## 7859 86883 Disabled
## 7860 77820 Not.in.Labor.Force
## 7861 7506 Retired
## EmploymentStatus.fctr.All.X..rcv.glmnet
## 7856 Not.in.Labor.Force
## 7857 Disabled
## 7858 Not.in.Labor.Force
## 7859 Employed
## 7860 Retired
## 7861 Employed
## EmploymentStatus.fctr.All.X..rcv.glmnet.prob
## 7856 0.3120301
## 7857 0.3111775
## 7858 0.3077395
## 7859 0.3036536
## 7860 0.2755269
## 7861 0.2743326
## EmploymentStatus.fctr.All.X..rcv.glmnet.err
## 7856 TRUE
## 7857 TRUE
## 7858 TRUE
## 7859 TRUE
## 7860 TRUE
## 7861 TRUE
## EmploymentStatus.fctr.All.X..rcv.glmnet.err.abs
## 7856 0.30214635
## 7857 0.05596686
## 7858 0.29883522
## 7859 0.29630243
## 7860 0.18757496
## 7861 0.24790773
## EmploymentStatus.fctr.All.X..rcv.glmnet.is.acc
## 7856 FALSE
## 7857 FALSE
## 7858 FALSE
## 7859 FALSE
## 7860 FALSE
## 7861 FALSE
## EmploymentStatus.fctr.All.X..rcv.glmnet.accurate
## 7856 FALSE
## 7857 FALSE
## 7858 FALSE
## 7859 FALSE
## 7860 FALSE
## 7861 FALSE
## EmploymentStatus.fctr.All.X..rcv.glmnet.error
## 7856 0.6879699
## 7857 0.6888225
## 7858 0.6922605
## 7859 0.6963464
## 7860 0.7244731
## 7861 0.7256674
if (!is.null(glbFeatsCategory)) {
glbLvlCategory <- merge(glbLvlCategory,
myget_category_stats(obs_df = glbObsFit, mdl_id = glb_sel_mdl_id,
label = "fit"),
by = glbFeatsCategory, all = TRUE)
row.names(glbLvlCategory) <- glbLvlCategory[, glbFeatsCategory]
glbLvlCategory <- merge(glbLvlCategory,
myget_category_stats(obs_df = glbObsOOB, mdl_id = glb_sel_mdl_id,
label="OOB"),
#by=glbFeatsCategory, all=TRUE) glb_ctgry-df already contains .n.OOB ?
all = TRUE)
row.names(glbLvlCategory) <- glbLvlCategory[, glbFeatsCategory]
if (any(grepl("OOB", glbMdlMetricsEval)))
print(orderBy(~-err.abs.OOB.mean, glbLvlCategory)) else
print(orderBy(~-err.abs.fit.mean, glbLvlCategory))
print(colSums(glbLvlCategory[, -grep(glbFeatsCategory, names(glbLvlCategory))]))
}## .category .n.OOB .n.Fit .n.Tst .freqRatio.Fit .freqRatio.OOB
## .dummy .dummy 28370 77143 25789 1 1
## .freqRatio.Tst err.abs.fit.sum err.abs.fit.mean .n.fit
## .dummy 1 3967.069 0.05142488 77143
## err.abs.OOB.sum err.abs.OOB.mean
## .dummy 1481.543 0.05222217
## .n.OOB .n.Fit .n.Tst .freqRatio.Fit
## 2.837000e+04 7.714300e+04 2.578900e+04 1.000000e+00
## .freqRatio.OOB .freqRatio.Tst err.abs.fit.sum err.abs.fit.mean
## 1.000000e+00 1.000000e+00 3.967069e+03 5.142488e-02
## .n.fit err.abs.OOB.sum err.abs.OOB.mean
## 7.714300e+04 1.481543e+03 5.222217e-02write.csv(glbObsOOB[, c(glbFeatsId,
grep(glb_rsp_var, names(glbObsOOB), fixed=TRUE, value=TRUE))],
paste0(gsub(".", "_", paste0(glbOut$pfx, glb_sel_mdl_id), fixed=TRUE),
"_OOBobs.csv"), row.names=FALSE)
fit.models_2_chunk_df <-
myadd_chunk(NULL, "fit.models_2_bgn", label.minor = "teardown")## label step_major step_minor label_minor bgn end elapsed
## 1 fit.models_2_bgn 1 0 teardown 1310.711 NA NAglb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.models", major.inc=FALSE)## label step_major step_minor label_minor bgn end elapsed
## 18 fit.models 8 2 2 1278.196 1310.739 32.544
## 19 fit.models 8 3 3 1310.740 NA NA# if (sum(is.na(glbObsAll$D.P.http)) > 0)
# stop("fit.models_3: Why is this happening ?")
#stop(here"); glb2Sav()
sync_glb_obs_df <- function() {
# Merge or cbind ?
for (col in setdiff(names(glbObsFit), names(glbObsTrn)))
glbObsTrn[glbObsTrn$.lcn == "Fit", col] <<- glbObsFit[, col]
for (col in setdiff(names(glbObsFit), names(glbObsAll)))
glbObsAll[glbObsAll$.lcn == "Fit", col] <<- glbObsFit[, col]
if (all(is.na(glbObsNew[, glb_rsp_var])))
for (col in setdiff(names(glbObsOOB), names(glbObsTrn)))
glbObsTrn[glbObsTrn$.lcn == "OOB", col] <<- glbObsOOB[, col]
for (col in setdiff(names(glbObsOOB), names(glbObsAll)))
glbObsAll[glbObsAll$.lcn == "OOB", col] <<- glbObsOOB[, col]
}
sync_glb_obs_df()
print(setdiff(names(glbObsNew), names(glbObsAll)))## character(0)replay.petrisim(pn = glb_analytics_pn,
replay.trans = (glb_analytics_avl_objs <- c(glb_analytics_avl_objs,
"model.selected")), flip_coord = TRUE)## time trans "bgn " "fit.data.training.all " "predict.data.new " "end "
## 0.0000 multiple enabled transitions: data.training.all data.new model.selected firing: data.training.all
## 1.0000 1 2 1 0 0
## 1.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction firing: data.new
## 2.0000 2 1 1 1 0
## 2.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction data.new.prediction firing: model.selected
## 3.0000 3 0 2 1 0
glb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.data.training", major.inc = TRUE)## label step_major step_minor label_minor bgn end
## 19 fit.models 8 3 3 1310.740 1331.742
## 20 fit.data.training 9 0 0 1331.743 NA
## elapsed
## 19 21.002
## 20 NAStep 9.0: fit data training
#load(paste0(glb_inp_pfx, "dsk.RData"))
if (!is.null(glb_fin_mdl_id) && (glb_fin_mdl_id %in% names(glb_models_lst))) {
warning("Final model same as user selected model")
glb_fin_mdl <- glb_models_lst[[glb_fin_mdl_id]]
} else
# if (nrow(glbObsFit) + length(glbObsFitOutliers) == nrow(glbObsTrn))
if (!all(is.na(glbObsNew[, glb_rsp_var])))
{
warning("Final model same as glb_sel_mdl_id")
glb_fin_mdl_id <- paste0("Final.", glb_sel_mdl_id)
glb_fin_mdl <- glb_sel_mdl
glb_models_lst[[glb_fin_mdl_id]] <- glb_fin_mdl
mdlDf <- glb_models_df[glb_models_df$id == glb_sel_mdl_id, ]
mdlDf$id <- glb_fin_mdl_id
glb_models_df <- rbind(glb_models_df, mdlDf)
} else {
if (grepl("RFE\\.X", names(glbMdlFamilies))) {
indepVar <- mygetIndepVar(glb_feats_df)
rfe_trn_results <-
myrun_rfe(glbObsTrn, indepVar, glbRFESizes[["Final"]])
if (!isTRUE(all.equal(sort(predictors(rfe_trn_results)),
sort(predictors(rfe_fit_results))))) {
print("Diffs predictors(rfe_trn_results) vs. predictors(rfe_fit_results):")
print(setdiff(predictors(rfe_trn_results), predictors(rfe_fit_results)))
print("Diffs predictors(rfe_fit_results) vs. predictors(rfe_trn_results):")
print(setdiff(predictors(rfe_fit_results), predictors(rfe_trn_results)))
}
}
# }
if (grepl("Ensemble", glb_sel_mdl_id)) {
# Find which models are relevant
mdlimp_df <- subset(myget_feats_importance(glb_sel_mdl), imp > 5)
# Fit selected models on glbObsTrn
for (mdl_id in gsub(".prob", "",
gsub(mygetPredictIds(glb_rsp_var)$value, "", row.names(mdlimp_df), fixed = TRUE),
fixed = TRUE)) {
mdl_id_components <- unlist(strsplit(mdl_id, "[.]"))
mdlIdPfx <- paste0(c(head(mdl_id_components, -1), "Train"),
collapse = ".")
if (grepl("RFE\\.X\\.", mdlIdPfx))
mdlIndepVars <- myadjustInteractionFeats(glb_feats_df, myextract_actual_feats(
predictors(rfe_trn_results))) else
mdlIndepVars <- trim(unlist(
strsplit(glb_models_df[glb_models_df$id == mdl_id, "feats"], "[,]")))
ret_lst <-
myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = mdlIdPfx,
type = glb_model_type, tune.df = glbMdlTuneParams,
trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = tail(mdl_id_components, 1))),
indepVar = mdlIndepVars,
rsp_var = glb_rsp_var,
fit_df = glbObsTrn, OOB_df = NULL)
glbObsTrn <- glb_get_predictions(df = glbObsTrn,
mdl_id = tail(glb_models_df$id, 1),
rsp_var = glb_rsp_var,
prob_threshold_def =
subset(glb_models_df, id == mdl_id)$opt.prob.threshold.OOB)
glbObsNew <- glb_get_predictions(df = glbObsNew,
mdl_id = tail(glb_models_df$id, 1),
rsp_var = glb_rsp_var,
prob_threshold_def =
subset(glb_models_df, id == mdl_id)$opt.prob.threshold.OOB)
}
}
# "Final" model
if ((model_method <- glb_sel_mdl$method) == "custom")
# get actual method from the mdl_id
model_method <- tail(unlist(strsplit(glb_sel_mdl_id, "[.]")), 1)
if (grepl("Ensemble", glb_sel_mdl_id)) {
# Find which models are relevant
mdlimp_df <- subset(myget_feats_importance(glb_sel_mdl), imp > 5)
if (glb_is_classification && glb_is_binomial)
indepVar <- gsub("(.*)\\.(.*)\\.prob", "\\1\\.Train\\.\\2\\.prob",
row.names(mdlimp_df)) else
indepVar <- gsub("(.*)\\.(.*)", "\\1\\.Train\\.\\2",
row.names(mdlimp_df))
} else
if (grepl("RFE.X", glb_sel_mdl_id, fixed = TRUE)) {
indepVar <- myextract_actual_feats(predictors(rfe_trn_results))
} else indepVar <-
trim(unlist(strsplit(glb_models_df[glb_models_df$id ==
glb_sel_mdl_id
, "feats"], "[,]")))
if (!is.null(glb_preproc_methods) &&
((match_pos <- regexpr(gsub(".", "\\.",
paste(glb_preproc_methods, collapse = "|"),
fixed = TRUE), glb_sel_mdl_id)) != -1))
ths_preProcess <- str_sub(glb_sel_mdl_id, match_pos,
match_pos + attr(match_pos, "match.length") - 1) else
ths_preProcess <- NULL
mdl_id_pfx <- ifelse(grepl("Ensemble", glb_sel_mdl_id),
"Final.Ensemble", "Final")
trnobs_df <- glbObsTrn
if (!is.null(glbObsTrnOutliers[[mdl_id_pfx]])) {
trnobs_df <- glbObsTrn[!(glbObsTrn[, glbFeatsId] %in% glbObsTrnOutliers[[mdl_id_pfx]]), ]
print(sprintf("Outliers removed: %d", nrow(glbObsTrn) - nrow(trnobs_df)))
print(setdiff(glbObsTrn[, glbFeatsId], trnobs_df[, glbFeatsId]))
}
# Force fitting of Final.glm to identify outliers
method_vctr <- unique(c(myparseMdlId(glb_sel_mdl_id)$alg, glbMdlFamilies[["Final"]]))
for (method in method_vctr) {
#source("caret_nominalTrainWorkflow.R")
# glmnet requires at least 2 indep vars
if ((length(indepVar) == 1) && (method %in% "glmnet"))
next
ret_lst <-
myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst = list(
id.prefix = mdl_id_pfx,
type = glb_model_type, trainControl.method = "repeatedcv",
trainControl.number = glb_rcv_n_folds,
trainControl.repeats = glb_rcv_n_repeats,
trainControl.classProbs = glb_is_classification,
trainControl.summaryFunction = glbMdlMetricSummaryFn,
trainControl.allowParallel = glbMdlAllowParallel,
train.metric = glbMdlMetricSummary,
train.maximize = glbMdlMetricMaximize,
train.method = method,
train.preProcess = ths_preProcess)),
indepVar = indepVar, rsp_var = glb_rsp_var,
fit_df = trnobs_df, OOB_df = NULL)
if ((length(method_vctr) == 1) || (method != "glm")) {
glb_fin_mdl <- glb_models_lst[[length(glb_models_lst)]]
glb_fin_mdl_id <- glb_models_df[length(glb_models_lst), "id"]
}
}
}## [1] "myfit_mdl: enter: 0.000000 secs"
## [1] "fitting model: Final##rcv#glmnet"
## [1] " indepVar: Age,Married.fctr,Education.fctr,Region.fctr,Race.fctr,.rnorm,Citizenship.fctr,Hispanic,Sex.fctr,PeopleInHousehold"
## [1] "myfit_mdl: setup complete: 0.738000 secs"
## + Fold1.Rep1: alpha=0.100, lambda=0.1013
## - Fold1.Rep1: alpha=0.100, lambda=0.1013
## + Fold1.Rep1: alpha=0.325, lambda=0.1013
## - Fold1.Rep1: alpha=0.325, lambda=0.1013
## + Fold1.Rep1: alpha=0.550, lambda=0.1013
## - Fold1.Rep1: alpha=0.550, lambda=0.1013
## + Fold1.Rep1: alpha=0.775, lambda=0.1013
## - Fold1.Rep1: alpha=0.775, lambda=0.1013
## + Fold1.Rep1: alpha=1.000, lambda=0.1013
## - Fold1.Rep1: alpha=1.000, lambda=0.1013
## + Fold2.Rep1: alpha=0.100, lambda=0.1013
## - Fold2.Rep1: alpha=0.100, lambda=0.1013
## + Fold2.Rep1: alpha=0.325, lambda=0.1013
## - Fold2.Rep1: alpha=0.325, lambda=0.1013
## + Fold2.Rep1: alpha=0.550, lambda=0.1013
## - Fold2.Rep1: alpha=0.550, lambda=0.1013
## + Fold2.Rep1: alpha=0.775, lambda=0.1013
## - Fold2.Rep1: alpha=0.775, lambda=0.1013
## + Fold2.Rep1: alpha=1.000, lambda=0.1013
## - Fold2.Rep1: alpha=1.000, lambda=0.1013
## + Fold3.Rep1: alpha=0.100, lambda=0.1013
## - Fold3.Rep1: alpha=0.100, lambda=0.1013
## + Fold3.Rep1: alpha=0.325, lambda=0.1013
## - Fold3.Rep1: alpha=0.325, lambda=0.1013
## + Fold3.Rep1: alpha=0.550, lambda=0.1013
## - Fold3.Rep1: alpha=0.550, lambda=0.1013
## + Fold3.Rep1: alpha=0.775, lambda=0.1013
## - Fold3.Rep1: alpha=0.775, lambda=0.1013
## + Fold3.Rep1: alpha=1.000, lambda=0.1013
## - Fold3.Rep1: alpha=1.000, lambda=0.1013
## + Fold1.Rep2: alpha=0.100, lambda=0.1013
## - Fold1.Rep2: alpha=0.100, lambda=0.1013
## + Fold1.Rep2: alpha=0.325, lambda=0.1013
## - Fold1.Rep2: alpha=0.325, lambda=0.1013
## + Fold1.Rep2: alpha=0.550, lambda=0.1013
## - Fold1.Rep2: alpha=0.550, lambda=0.1013
## + Fold1.Rep2: alpha=0.775, lambda=0.1013
## - Fold1.Rep2: alpha=0.775, lambda=0.1013
## + Fold1.Rep2: alpha=1.000, lambda=0.1013
## - Fold1.Rep2: alpha=1.000, lambda=0.1013
## + Fold2.Rep2: alpha=0.100, lambda=0.1013
## - Fold2.Rep2: alpha=0.100, lambda=0.1013
## + Fold2.Rep2: alpha=0.325, lambda=0.1013
## - Fold2.Rep2: alpha=0.325, lambda=0.1013
## + Fold2.Rep2: alpha=0.550, lambda=0.1013
## - Fold2.Rep2: alpha=0.550, lambda=0.1013
## + Fold2.Rep2: alpha=0.775, lambda=0.1013
## - Fold2.Rep2: alpha=0.775, lambda=0.1013
## + Fold2.Rep2: alpha=1.000, lambda=0.1013
## - Fold2.Rep2: alpha=1.000, lambda=0.1013
## + Fold3.Rep2: alpha=0.100, lambda=0.1013
## - Fold3.Rep2: alpha=0.100, lambda=0.1013
## + Fold3.Rep2: alpha=0.325, lambda=0.1013
## - Fold3.Rep2: alpha=0.325, lambda=0.1013
## + Fold3.Rep2: alpha=0.550, lambda=0.1013
## - Fold3.Rep2: alpha=0.550, lambda=0.1013
## + Fold3.Rep2: alpha=0.775, lambda=0.1013
## - Fold3.Rep2: alpha=0.775, lambda=0.1013
## + Fold3.Rep2: alpha=1.000, lambda=0.1013
## - Fold3.Rep2: alpha=1.000, lambda=0.1013
## + Fold1.Rep3: alpha=0.100, lambda=0.1013
## - Fold1.Rep3: alpha=0.100, lambda=0.1013
## + Fold1.Rep3: alpha=0.325, lambda=0.1013
## - Fold1.Rep3: alpha=0.325, lambda=0.1013
## + Fold1.Rep3: alpha=0.550, lambda=0.1013
## - Fold1.Rep3: alpha=0.550, lambda=0.1013
## + Fold1.Rep3: alpha=0.775, lambda=0.1013
## - Fold1.Rep3: alpha=0.775, lambda=0.1013
## + Fold1.Rep3: alpha=1.000, lambda=0.1013
## - Fold1.Rep3: alpha=1.000, lambda=0.1013
## + Fold2.Rep3: alpha=0.100, lambda=0.1013
## - Fold2.Rep3: alpha=0.100, lambda=0.1013
## + Fold2.Rep3: alpha=0.325, lambda=0.1013
## - Fold2.Rep3: alpha=0.325, lambda=0.1013
## + Fold2.Rep3: alpha=0.550, lambda=0.1013
## - Fold2.Rep3: alpha=0.550, lambda=0.1013
## + Fold2.Rep3: alpha=0.775, lambda=0.1013
## - Fold2.Rep3: alpha=0.775, lambda=0.1013
## + Fold2.Rep3: alpha=1.000, lambda=0.1013
## - Fold2.Rep3: alpha=1.000, lambda=0.1013
## + Fold3.Rep3: alpha=0.100, lambda=0.1013
## - Fold3.Rep3: alpha=0.100, lambda=0.1013
## + Fold3.Rep3: alpha=0.325, lambda=0.1013
## - Fold3.Rep3: alpha=0.325, lambda=0.1013
## + Fold3.Rep3: alpha=0.550, lambda=0.1013
## - Fold3.Rep3: alpha=0.550, lambda=0.1013
## + Fold3.Rep3: alpha=0.775, lambda=0.1013
## - Fold3.Rep3: alpha=0.775, lambda=0.1013
## + Fold3.Rep3: alpha=1.000, lambda=0.1013
## - Fold3.Rep3: alpha=1.000, lambda=0.1013
## Aggregating results
## Selecting tuning parameters
## Fitting alpha = 1, lambda = 0.000218 on full training set
## [1] "myfit_mdl: train complete: 1637.374000 secs"## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = mdl_id_pfx, : model's bestTune found at an extreme of
## tuneGrid for parameter: alpha## Warning in myfit_mdl(mdl_specs_lst = myinit_mdl_specs_lst(mdl_specs_lst
## = list(id.prefix = mdl_id_pfx, : model's bestTune found at an extreme of
## tuneGrid for parameter: lambda
## Length Class Mode
## a0 370 -none- numeric
## beta 5 -none- list
## dfmat 370 -none- numeric
## df 74 -none- numeric
## dim 2 -none- numeric
## lambda 74 -none- numeric
## dev.ratio 74 -none- numeric
## nulldev 1 -none- numeric
## npasses 1 -none- numeric
## jerr 1 -none- numeric
## offset 1 -none- logical
## classnames 5 -none- character
## grouped 1 -none- logical
## call 5 -none- call
## nobs 1 -none- numeric
## lambdaOpt 1 -none- numeric
## xNames 28 -none- character
## problemType 1 -none- character
## tuneValue 2 data.frame list
## obsLevels 5 -none- character
## [1] "min lambda > lambdaOpt:"
## [1] "class: Disabled:"
##
## -0.63888122
## Age
## 0.05231109
## Citizenship.fctrCitizen, Naturalized
## -0.49033684
## Citizenship.fctrNon-Citizen
## -0.85384229
## Education.fctrBachelor's degree
## -0.67620626
## Education.fctrDoctorate degree
## -0.58200084
## Education.fctrHigh school
## 0.35014528
## Education.fctrMaster's degree
## -0.84578839
## Education.fctrNo high school diploma
## 1.05787757
## Education.fctrProfessional degree
## -0.83105312
## Education.fctrSome college, no degree
## 0.04352802
## Married.fctrMarried
## -0.85948490
## Married.fctrSeparated
## 0.21805484
## PeopleInHousehold
## -0.02475525
## Race.fctrAmerican Indian
## 0.06003993
## Race.fctrAsian
## -0.05776675
## Race.fctrBlack
## 0.34753090
## Race.fctrMultiracial
## 0.06472791
## Race.fctrPacific Islander
## 0.17134900
## Region.fctrMidwest
## -0.07553574
## Region.fctrNortheast
## -0.03254712
## Region.fctrWest
## -0.11142301
## [1] "class: Employed:"
##
## 4.037424167
## .rnorm
## 0.005725224
## Citizenship.fctrCitizen, Naturalized
## 0.072911872
## Citizenship.fctrNon-Citizen
## 0.106329047
## Education.fctrBachelor's degree
## 0.150025880
## Education.fctrDoctorate degree
## 0.737594465
## Education.fctrHigh school
## -0.432415002
## Education.fctrMaster's degree
## 0.299525848
## Education.fctrNo high school diploma
## -0.821219124
## Education.fctrProfessional degree
## 0.587187423
## Education.fctrSome college, no degree
## -0.204319003
## Hispanic
## 0.066151756
## Married.fctrNever Married
## -0.198578021
## Married.fctrWidowed
## -0.046795531
## Race.fctrAmerican Indian
## -0.304628331
## Race.fctrBlack
## -0.163732768
## Race.fctrMultiracial
## -0.202447200
## Race.fctrPacific Islander
## -0.062622824
## Region.fctrMidwest
## 0.158275969
## Region.fctrNortheast
## 0.060652531
## Region.fctrWest
## -0.022935468
## Sex.fctrMale
## 0.214773719
## [1] "class: Not.in.Labor.Force:"
##
## 3.20010813
## Age
## -0.04104332
## Citizenship.fctrNon-Citizen
## 0.16845202
## Education.fctrHigh school
## 0.00659570
## Education.fctrMaster's degree
## -0.03622108
## Education.fctrNo high school diploma
## 0.97788073
## Education.fctrSome college, no degree
## 0.25406019
## Hispanic
## -0.09148494
## Married.fctrMarried
## 0.24292446
## Married.fctrNever Married
## 0.32482603
## Married.fctrSeparated
## -0.02523701
## Married.fctrWidowed
## 0.66714724
## PeopleInHousehold
## 0.15067149
## Race.fctrAsian
## 0.44167139
## Race.fctrBlack
## -0.04575543
## Region.fctrMidwest
## -0.10758757
## Sex.fctrMale
## -0.73270833
## [1] "class: Retired:"
## .rnorm
## -7.79769527 -0.02223912
## Age Citizenship.fctrCitizen, Naturalized
## 0.18109988 -0.21892704
## Citizenship.fctrNon-Citizen Education.fctrBachelor's degree
## -0.28632489 0.08222431
## Education.fctrHigh school Education.fctrMaster's degree
## -0.06603050 0.26445231
## Married.fctrMarried Married.fctrNever Married
## 0.36846243 -0.07385050
## Married.fctrSeparated Married.fctrWidowed
## -0.14254986 0.53991113
## PeopleInHousehold Race.fctrAmerican Indian
## -0.16091689 -0.03108225
## Race.fctrAsian Race.fctrMultiracial
## 0.13693219 -0.14565247
## Race.fctrPacific Islander Region.fctrNortheast
## -0.01435219 -0.06200164
## Region.fctrWest Sex.fctrMale
## 0.04968121 -0.10215077
## [1] "class: Unemployed:"
## Age
## 1.199044190 -0.005001215
## Education.fctrNo high school diploma Hispanic
## -0.089470493 0.138530924
## Married.fctrMarried Married.fctrNever Married
## -0.566750536 0.005308366
## Married.fctrWidowed PeopleInHousehold
## -0.055625871 0.074743995
## Race.fctrAmerican Indian Race.fctrBlack
## 0.372819157 0.528513290
## Race.fctrMultiracial Race.fctrPacific Islander
## 0.092689898 0.077943957
## Region.fctrMidwest Region.fctrNortheast
## 0.045924146 0.154696199
## Region.fctrWest Sex.fctrMale
## 0.075284939 0.169018182
## [1] "max lambda < lambdaOpt:"
## [1] "Feats mismatch between coefs_left & rght:"
## [1] ""
## [2] ".rnorm"
## [3] "Age"
## [4] "Citizenship.fctrCitizen, Naturalized"
## [5] "Citizenship.fctrNon-Citizen"
## [6] "Education.fctrBachelor's degree"
## [7] "Education.fctrDoctorate degree"
## [8] "Education.fctrHigh school"
## [9] "Education.fctrMaster's degree"
## [10] "Education.fctrNA.my"
## [11] "Education.fctrNo high school diploma"
## [12] "Education.fctrProfessional degree"
## [13] "Education.fctrSome college, no degree"
## [14] "Hispanic"
## [15] "Married.fctrMarried"
## [16] "Married.fctrNA.my"
## [17] "Married.fctrNever Married"
## [18] "Married.fctrSeparated"
## [19] "Married.fctrWidowed"
## [20] "PeopleInHousehold"
## [21] "Race.fctrAmerican Indian"
## [22] "Race.fctrAsian"
## [23] "Race.fctrBlack"
## [24] "Race.fctrMultiracial"
## [25] "Race.fctrPacific Islander"
## [26] "Region.fctrMidwest"
## [27] "Region.fctrNortheast"
## [28] "Region.fctrWest"
## [29] "Sex.fctrMale"
## [1] "myfit_mdl: train diagnostics complete: 1638.228000 secs"
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 281 4356 268 807
## Employed 151 56382 2238 2962
## Not.in.Labor.Force 52 8959 5844 391
## Retired 110 4603 26 13880
## Unemployed 19 3527 511 146
## Prediction
## Reference Unemployed
## Disabled 0
## Employed 0
## Not.in.Labor.Force 0
## Retired 0
## Unemployed 0
## Accuracy Kappa AccuracyLower AccuracyUpper AccuracyNull
## 0.7239582 0.4747524 0.7212500 0.7266541 0.5850748
## AccuracyPValue McnemarPValue
## 0.0000000 0.0000000
## [1] "myfit_mdl: predict complete: 1640.102000 secs"
## id
## 1 Final##rcv#glmnet
## feats
## 1 Age,Married.fctr,Education.fctr,Region.fctr,Race.fctr,.rnorm,Citizenship.fctr,Hispanic,Sex.fctr,PeopleInHousehold
## max.nTuningRuns min.elapsedtime.everything min.elapsedtime.final
## 1 25 1636.356 44.8
## max.Accuracy.fit max.AccuracyLower.fit max.AccuracyUpper.fit
## 1 0.723895 0.72125 0.7266541
## max.Kappa.fit max.AccuracySD.fit max.KappaSD.fit
## 1 0.4745565 0.001551918 0.002809817
## [1] "myfit_mdl: exit: 1640.112000 secs"rm(ret_lst)
glb_chunks_df <- myadd_chunk(glb_chunks_df, "fit.data.training", major.inc=FALSE)## label step_major step_minor label_minor bgn end
## 20 fit.data.training 9 0 0 1331.743 2972.311
## 21 fit.data.training 9 1 1 2972.312 NA
## elapsed
## 20 1640.568
## 21 NA#stop(here"); glb2Sav()
if (glb_is_classification && glb_is_binomial)
prob_threshold <- glb_models_df[glb_models_df$id == glb_sel_mdl_id,
"opt.prob.threshold.OOB"] else
prob_threshold <- NULL
if (grepl("Ensemble", glb_fin_mdl_id)) {
# Get predictions for each model in ensemble; Outliers that have been moved to OOB might not have been predicted yet
mdlEnsembleComps <- unlist(str_split(subset(glb_models_df,
id == glb_fin_mdl_id)$feats, ","))
if (glb_is_classification && glb_is_binomial)
mdlEnsembleComps <- gsub("\\.prob$", "", mdlEnsembleComps)
mdlEnsembleComps <- gsub(paste0("^",
gsub(".", "\\.", mygetPredictIds(glb_rsp_var)$value, fixed = TRUE)),
"", mdlEnsembleComps)
for (mdl_id in mdlEnsembleComps) {
glbObsTrn <- glb_get_predictions(df = glbObsTrn, mdl_id = mdl_id,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)
glbObsNew <- glb_get_predictions(df = glbObsNew, mdl_id = mdl_id,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)
}
}
glbObsTrn <- glb_get_predictions(df = glbObsTrn, mdl_id = glb_fin_mdl_id,
rsp_var = glb_rsp_var,
prob_threshold_def = prob_threshold)
glb_featsimp_df <- myget_feats_importance(mdl=glb_fin_mdl,
featsimp_df=glb_featsimp_df)
#glb_featsimp_df[, paste0(glb_fin_mdl_id, ".imp")] <- glb_featsimp_df$imp
print(glb_featsimp_df)## All.X..rcv.glmnet.imp.Disabled
## .rnorm 1.5250461
## Age 4.9502539
## Citizenship.fctrCitizen, Naturalized 47.4802548
## Citizenship.fctrNon-Citizen 80.8187616
## Education.fctrBachelor's degree 59.1559838
## Education.fctrDoctorate degree 58.8506019
## Education.fctrHigh school 34.0699104
## Education.fctrMaster's degree 81.6105115
## Education.fctrNA.my 0.0000000
## Education.fctrNo high school diploma 100.0000000
## Education.fctrProfessional degree 71.1360427
## Education.fctrSome college, no degree 10.8622226
## Hispanic 0.0000000
## Married.fctrMarried 80.5845919
## Married.fctrNA.my 0.0000000
## Married.fctrNever Married 0.0000000
## Married.fctrSeparated 15.0539265
## Married.fctrWidowed 0.0000000
## PeopleInHousehold 1.5572023
## Race.fctrAmerican Indian 0.8471631
## Race.fctrAsian 6.8442014
## Race.fctrBlack 29.1551897
## Race.fctrMultiracial 8.6753643
## Race.fctrPacific Islander 25.8652446
## Region.fctrMidwest 6.7340630
## Region.fctrNortheast 1.5329980
## Region.fctrWest 9.8859677
## Sex.fctrMale 0.0000000
## All.X..rcv.glmnet.imp.Employed
## .rnorm 1.061148
## Age 0.000000
## Citizenship.fctrCitizen, Naturalized 7.787895
## Citizenship.fctrNon-Citizen 7.227984
## Education.fctrBachelor's degree 14.350902
## Education.fctrDoctorate degree 72.186222
## Education.fctrHigh school 42.836408
## Education.fctrMaster's degree 24.226282
## Education.fctrNA.my 0.000000
## Education.fctrNo high school diploma 80.094677
## Education.fctrProfessional degree 50.306390
## Education.fctrSome college, no degree 20.401790
## Hispanic 5.086637
## Married.fctrMarried 0.000000
## Married.fctrNA.my 0.000000
## Married.fctrNever Married 19.383808
## Married.fctrSeparated 0.000000
## Married.fctrWidowed 11.058165
## PeopleInHousehold 0.000000
## Race.fctrAmerican Indian 34.669462
## Race.fctrAsian 0.000000
## Race.fctrBlack 19.032460
## Race.fctrMultiracial 12.038783
## Race.fctrPacific Islander 15.024038
## Region.fctrMidwest 13.781795
## Region.fctrNortheast 8.249320
## Region.fctrWest 0.000000
## Sex.fctrMale 20.843611
## All.X..rcv.glmnet.imp.Not.in.Labor.Force
## .rnorm 0.000000
## Age 3.879180
## Citizenship.fctrCitizen, Naturalized 3.886102
## Citizenship.fctrNon-Citizen 14.922307
## Education.fctrBachelor's degree 0.000000
## Education.fctrDoctorate degree 0.000000
## Education.fctrHigh school 0.000000
## Education.fctrMaster's degree 3.826702
## Education.fctrNA.my 0.000000
## Education.fctrNo high school diploma 90.911477
## Education.fctrProfessional degree 0.000000
## Education.fctrSome college, no degree 21.607572
## Hispanic 9.740632
## Married.fctrMarried 24.377008
## Married.fctrNA.my 0.000000
## Married.fctrNever Married 31.347716
## Married.fctrSeparated 3.525010
## Married.fctrWidowed 54.767522
## PeopleInHousehold 13.790449
## Race.fctrAmerican Indian 0.000000
## Race.fctrAsian 41.270984
## Race.fctrBlack 8.553671
## Race.fctrMultiracial 5.097845
## Race.fctrPacific Islander 0.000000
## Region.fctrMidwest 14.084344
## Region.fctrNortheast 0.000000
## Region.fctrWest 0.000000
## Sex.fctrMale 67.291846
## All.X..rcv.glmnet.imp.Retired
## .rnorm 1.5581039
## Age 16.9487180
## Citizenship.fctrCitizen, Naturalized 19.7809372
## Citizenship.fctrNon-Citizen 27.3778456
## Education.fctrBachelor's degree 3.8671767
## Education.fctrDoctorate degree 3.2717620
## Education.fctrHigh school 7.1433732
## Education.fctrMaster's degree 22.1583093
## Education.fctrNA.my 0.0000000
## Education.fctrNo high school diploma 0.0000000
## Education.fctrProfessional degree 0.0000000
## Education.fctrSome college, no degree 0.0000000
## Hispanic 0.0000000
## Married.fctrMarried 38.3635891
## Married.fctrNA.my 0.0000000
## Married.fctrNever Married 4.6328211
## Married.fctrSeparated 20.2361192
## Married.fctrWidowed 49.5531148
## PeopleInHousehold 14.9510504
## Race.fctrAmerican Indian 16.9468444
## Race.fctrAsian 14.0094019
## Race.fctrBlack 0.0000000
## Race.fctrMultiracial 10.5548579
## Race.fctrPacific Islander 17.3463875
## Region.fctrMidwest 0.0000000
## Region.fctrNortheast 0.1003404
## Region.fctrWest 7.5367906
## Sex.fctrMale 10.5284526
## All.X..rcv.glmnet.imp.Unemployed
## .rnorm 0.0000000
## Age 0.3375848
## Citizenship.fctrCitizen, Naturalized 0.0000000
## Citizenship.fctrNon-Citizen 0.0000000
## Education.fctrBachelor's degree 0.0000000
## Education.fctrDoctorate degree 0.0000000
## Education.fctrHigh school 0.5911445
## Education.fctrMaster's degree 0.0000000
## Education.fctrNA.my 0.0000000
## Education.fctrNo high school diploma 11.0521930
## Education.fctrProfessional degree 0.0000000
## Education.fctrSome college, no degree 0.3188346
## Hispanic 16.0729143
## Married.fctrMarried 50.7011130
## Married.fctrNA.my 0.0000000
## Married.fctrNever Married 2.4655739
## Married.fctrSeparated 5.3005399
## Married.fctrWidowed 10.6888708
## PeopleInHousehold 6.7356407
## Race.fctrAmerican Indian 21.2926566
## Race.fctrAsian 5.1886845
## Race.fctrBlack 46.9542665
## Race.fctrMultiracial 0.0000000
## Race.fctrPacific Islander 2.6089982
## Region.fctrMidwest 3.2572087
## Region.fctrNortheast 14.1844916
## Region.fctrWest 8.5521108
## Sex.fctrMale 21.5884246
## Final..rcv.glmnet.imp.Disabled
## .rnorm 0.000000
## Age 4.944910
## Citizenship.fctrCitizen, Naturalized 46.351000
## Citizenship.fctrNon-Citizen 80.712770
## Education.fctrBachelor's degree 63.921032
## Education.fctrDoctorate degree 55.015897
## Education.fctrHigh school 33.098847
## Education.fctrMaster's degree 79.951444
## Education.fctrNA.my 0.000000
## Education.fctrNo high school diploma 100.000000
## Education.fctrProfessional degree 78.558535
## Education.fctrSome college, no degree 4.114656
## Hispanic 0.000000
## Married.fctrMarried 81.246159
## Married.fctrNA.my 0.000000
## Married.fctrNever Married 0.000000
## Married.fctrSeparated 20.612483
## Married.fctrWidowed 0.000000
## PeopleInHousehold 2.340087
## Race.fctrAmerican Indian 5.675508
## Race.fctrAsian 5.460627
## Race.fctrBlack 32.851713
## Race.fctrMultiracial 6.118658
## Race.fctrPacific Islander 16.197432
## Region.fctrMidwest 7.140310
## Region.fctrNortheast 3.076644
## Region.fctrWest 10.532694
## Sex.fctrMale 0.000000
## Final..rcv.glmnet.imp.Employed
## .rnorm 0.5411991
## Age 0.0000000
## Citizenship.fctrCitizen, Naturalized 6.8922788
## Citizenship.fctrNon-Citizen 10.0511675
## Education.fctrBachelor's degree 14.1817810
## Education.fctrDoctorate degree 69.7239913
## Education.fctrHigh school 40.8757133
## Education.fctrMaster's degree 28.3138481
## Education.fctrNA.my 0.0000000
## Education.fctrNo high school diploma 77.6289381
## Education.fctrProfessional degree 55.5061795
## Education.fctrSome college, no degree 19.3140500
## Hispanic 6.2532525
## Married.fctrMarried 0.0000000
## Married.fctrNA.my 0.0000000
## Married.fctrNever Married 18.7713613
## Married.fctrSeparated 0.0000000
## Married.fctrWidowed 4.4235299
## PeopleInHousehold 0.0000000
## Race.fctrAmerican Indian 28.7961802
## Race.fctrAsian 0.0000000
## Race.fctrBlack 15.4774780
## Race.fctrMultiracial 19.1371106
## Race.fctrPacific Islander 5.9196665
## Region.fctrMidwest 14.9616528
## Region.fctrNortheast 5.7334168
## Region.fctrWest 2.1680645
## Sex.fctrMale 20.3023228
## Final..rcv.glmnet.imp.Not.in.Labor.Force
## .rnorm 0.0000000
## Age 3.8797797
## Citizenship.fctrCitizen, Naturalized 0.0000000
## Citizenship.fctrNon-Citizen 15.9235833
## Education.fctrBachelor's degree 0.0000000
## Education.fctrDoctorate degree 0.0000000
## Education.fctrHigh school 0.6234842
## Education.fctrMaster's degree 3.4239386
## Education.fctrNA.my 0.0000000
## Education.fctrNo high school diploma 92.4379866
## Education.fctrProfessional degree 0.0000000
## Education.fctrSome college, no degree 24.0160296
## Hispanic 8.6479709
## Married.fctrMarried 22.9633810
## Married.fctrNA.my 0.0000000
## Married.fctrNever Married 30.7054464
## Married.fctrSeparated 2.3856269
## Married.fctrWidowed 63.0646928
## PeopleInHousehold 14.2428100
## Race.fctrAmerican Indian 0.0000000
## Race.fctrAsian 41.7507091
## Race.fctrBlack 4.3252103
## Race.fctrMultiracial 0.0000000
## Race.fctrPacific Islander 0.0000000
## Region.fctrMidwest 10.1701343
## Region.fctrNortheast 0.0000000
## Region.fctrWest 0.0000000
## Sex.fctrMale 69.2621101
## Final..rcv.glmnet.imp.Retired
## .rnorm 2.102239
## Age 17.119172
## Citizenship.fctrCitizen, Naturalized 20.694932
## Citizenship.fctrNon-Citizen 27.065976
## Education.fctrBachelor's degree 7.772573
## Education.fctrDoctorate degree 0.000000
## Education.fctrHigh school 6.241790
## Education.fctrMaster's degree 24.998385
## Education.fctrNA.my 0.000000
## Education.fctrNo high school diploma 0.000000
## Education.fctrProfessional degree 0.000000
## Education.fctrSome college, no degree 0.000000
## Hispanic 0.000000
## Married.fctrMarried 34.830347
## Married.fctrNA.my 0.000000
## Married.fctrNever Married 6.981007
## Married.fctrSeparated 13.475081
## Married.fctrWidowed 51.037204
## PeopleInHousehold 15.211297
## Race.fctrAmerican Indian 2.938171
## Race.fctrAsian 12.944049
## Race.fctrBlack 0.000000
## Race.fctrMultiracial 13.768367
## Race.fctrPacific Islander 1.356697
## Region.fctrMidwest 0.000000
## Region.fctrNortheast 5.860947
## Region.fctrWest 4.696310
## Sex.fctrMale 9.656200
## Final..rcv.glmnet.imp.Unemployed imp
## .rnorm 0.0000000 -1
## Age 0.4727594 -2
## Citizenship.fctrCitizen, Naturalized 0.0000000 -3
## Citizenship.fctrNon-Citizen 0.0000000 -4
## Education.fctrBachelor's degree 0.0000000 -5
## Education.fctrDoctorate degree 0.0000000 -6
## Education.fctrHigh school 0.0000000 -7
## Education.fctrMaster's degree 0.0000000 -8
## Education.fctrNA.my 0.0000000 -9
## Education.fctrNo high school diploma 8.4575470 -10
## Education.fctrProfessional degree 0.0000000 -11
## Education.fctrSome college, no degree 0.0000000 -12
## Hispanic 13.0951755 -13
## Married.fctrMarried 53.5743032 -14
## Married.fctrNA.my 0.0000000 -15
## Married.fctrNever Married 0.5017940 -16
## Married.fctrSeparated 0.0000000 -17
## Married.fctrWidowed 5.2582522 -18
## PeopleInHousehold 7.0654674 -19
## Race.fctrAmerican Indian 35.2421838 -20
## Race.fctrAsian 0.0000000 -21
## Race.fctrBlack 49.9597784 -22
## Race.fctrMultiracial 8.7618738 -23
## Race.fctrPacific Islander 7.3679563 -24
## Region.fctrMidwest 4.3411589 -25
## Region.fctrNortheast 14.6232611 -26
## Region.fctrWest 7.1166022 -27
## Sex.fctrMale 15.9771023 -28if (glb_is_classification && glb_is_binomial)
glb_analytics_diag_plots(obs_df=glbObsTrn, mdl_id=glb_fin_mdl_id,
prob_threshold=glb_models_df[glb_models_df$id == glb_sel_mdl_id,
"opt.prob.threshold.OOB"]) else
glb_analytics_diag_plots(obs_df=glbObsTrn, mdl_id=glb_fin_mdl_id) ## Warning in glb_analytics_diag_plots(obs_df = glbObsTrn, mdl_id =
## glb_fin_mdl_id): Limiting important feature scatter plots to 5 out of 10
## [1] "Min/Max Boundaries: "
## .rownames EmploymentStatus.fctr EmploymentStatus.fctr.All.X..rcv.glmnet
## 1 92232 Retired Retired
## 2 91473 Not.in.Labor.Force <NA>
## 3 82324 Employed <NA>
## 4 80194 Disabled Retired
## 5 55388 Disabled Retired
## 6 73495 Disabled Retired
## 7 57377 Not.in.Labor.Force Retired
## 8 111997 Disabled Retired
## 9 123652 Not.in.Labor.Force <NA>
## 10 55065 Disabled <NA>
## 11 33583 Disabled Not.in.Labor.Force
## 12 34152 Not.in.Labor.Force Employed
## 13 34149 Disabled Not.in.Labor.Force
## 14 57503 Employed Not.in.Labor.Force
## 15 55993 Not.in.Labor.Force Employed
## 16 114440 Not.in.Labor.Force Employed
## EmploymentStatus.fctr.All.X..rcv.glmnet.prob
## 1 0.9466763
## 2 NA
## 3 NA
## 4 0.9641804
## 5 0.9616346
## 6 0.9610895
## 7 0.9574020
## 8 0.9331917
## 9 NA
## 10 NA
## 11 0.7670838
## 12 0.7179204
## 13 0.5753285
## 14 0.5475758
## 15 0.4783561
## 16 0.4410888
## EmploymentStatus.fctr.All.X..rcv.glmnet.err
## 1 FALSE
## 2 NA
## 3 NA
## 4 TRUE
## 5 TRUE
## 6 TRUE
## 7 TRUE
## 8 TRUE
## 9 NA
## 10 NA
## 11 TRUE
## 12 TRUE
## 13 TRUE
## 14 TRUE
## 15 TRUE
## 16 TRUE
## EmploymentStatus.fctr.All.X..rcv.glmnet.err.abs
## 1 0.000000000
## 2 NA
## 3 NA
## 4 0.015755430
## 5 0.024267880
## 6 0.023343962
## 7 0.000793178
## 8 0.052234638
## 9 NA
## 10 NA
## 11 0.023841333
## 12 0.172575843
## 13 0.038986105
## 14 0.351226657
## 15 0.392210213
## 16 0.433120978
## EmploymentStatus.fctr.All.X..rcv.glmnet.is.acc
## 1 TRUE
## 2 NA
## 3 NA
## 4 FALSE
## 5 FALSE
## 6 FALSE
## 7 FALSE
## 8 FALSE
## 9 NA
## 10 NA
## 11 FALSE
## 12 FALSE
## 13 FALSE
## 14 FALSE
## 15 FALSE
## 16 FALSE
## EmploymentStatus.fctr.Final..rcv.glmnet
## 1 Retired
## 2 Not.in.Labor.Force
## 3 Employed
## 4 Retired
## 5 Retired
## 6 Retired
## 7 Retired
## 8 Retired
## 9 Retired
## 10 Retired
## 11 Not.in.Labor.Force
## 12 Employed
## 13 Not.in.Labor.Force
## 14 Not.in.Labor.Force
## 15 Employed
## 16 Employed
## EmploymentStatus.fctr.Final..rcv.glmnet.prob
## 1 0.9486844
## 2 0.6513522
## 3 0.7776858
## 4 0.9654976
## 5 0.9630189
## 6 0.9618780
## 7 0.9586793
## 8 0.9349725
## 9 0.8837644
## 10 0.8360837
## 11 0.7622472
## 12 0.7207351
## 13 0.5656594
## 14 0.5330480
## 15 0.4785182
## 16 0.4436580
## EmploymentStatus.fctr.Final..rcv.glmnet.err
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 TRUE
## 5 TRUE
## 6 TRUE
## 7 TRUE
## 8 TRUE
## 9 TRUE
## 10 TRUE
## 11 TRUE
## 12 TRUE
## 13 TRUE
## 14 TRUE
## 15 TRUE
## 16 TRUE
## EmploymentStatus.fctr.Final..rcv.glmnet.err.abs
## 1 0.0000000000
## 2 0.0000000000
## 3 0.0000000000
## 4 0.0143991713
## 5 0.0226915610
## 6 0.0221760536
## 7 0.0008187548
## 8 0.0501773379
## 9 0.0089483302
## 10 0.1403765993
## 11 0.0237390119
## 12 0.1696334648
## 13 0.0398646937
## 14 0.3614746510
## 15 0.3939317654
## 16 0.4318972297
## EmploymentStatus.fctr.Final..rcv.glmnet.is.acc
## 1 TRUE
## 2 TRUE
## 3 TRUE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## 7 FALSE
## 8 FALSE
## 9 FALSE
## 10 FALSE
## 11 FALSE
## 12 FALSE
## 13 FALSE
## 14 FALSE
## 15 FALSE
## 16 FALSE
## EmploymentStatus.fctr.Final..rcv.glmnet.accurate
## 1 TRUE
## 2 TRUE
## 3 TRUE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## 7 FALSE
## 8 FALSE
## 9 FALSE
## 10 FALSE
## 11 FALSE
## 12 FALSE
## 13 FALSE
## 14 FALSE
## 15 FALSE
## 16 FALSE
## EmploymentStatus.fctr.Final..rcv.glmnet.error .label
## 1 0.00000000 92232
## 2 0.00000000 91473
## 3 0.00000000 82324
## 4 0.03450237 80194
## 5 0.03698107 55388
## 6 0.03812201 73495
## 7 0.04132066 57377
## 8 0.06502753 111997
## 9 0.11623560 123652
## 10 0.16391630 55065
## 11 0.23775277 33583
## 12 0.27926488 34152
## 13 0.43434061 34149
## 14 0.46695196 57503
## 15 0.52148185 55993
## 16 0.55634204 114440
## [1] "Inaccurate: "
## .rownames EmploymentStatus.fctr EmploymentStatus.fctr.All.X..rcv.glmnet
## 1 73130 Disabled Retired
## 2 35230 Not.in.Labor.Force Retired
## 3 66446 Disabled Retired
## 4 30168 Employed <NA>
## 5 74437 Disabled <NA>
## 6 11251 Disabled Retired
## EmploymentStatus.fctr.All.X..rcv.glmnet.prob
## 1 0.9736238
## 2 0.9726779
## 3 0.9702989
## 4 NA
## 5 NA
## 6 0.9709380
## EmploymentStatus.fctr.All.X..rcv.glmnet.err
## 1 TRUE
## 2 TRUE
## 3 TRUE
## 4 NA
## 5 NA
## 6 TRUE
## EmploymentStatus.fctr.All.X..rcv.glmnet.err.abs
## 1 0.0064589096
## 2 0.0007402925
## 3 0.0079048628
## 4 NA
## 5 NA
## 6 0.0141980346
## EmploymentStatus.fctr.All.X..rcv.glmnet.is.acc
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 NA
## 5 NA
## 6 FALSE
## EmploymentStatus.fctr.Final..rcv.glmnet
## 1 Retired
## 2 Retired
## 3 Retired
## 4 Retired
## 5 Retired
## 6 Retired
## EmploymentStatus.fctr.Final..rcv.glmnet.prob
## 1 0.9748694
## 2 0.9723952
## 3 0.9721108
## 4 0.9719574
## 5 0.9717480
## 6 0.9716955
## EmploymentStatus.fctr.Final..rcv.glmnet.err
## 1 TRUE
## 2 TRUE
## 3 TRUE
## 4 TRUE
## 5 TRUE
## 6 TRUE
## EmploymentStatus.fctr.Final..rcv.glmnet.err.abs
## 1 0.005875948
## 2 0.000796662
## 3 0.006977207
## 4 0.015728671
## 5 0.013072004
## 6 0.013093493
## EmploymentStatus.fctr.Final..rcv.glmnet.is.acc
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## EmploymentStatus.fctr.Final..rcv.glmnet.accurate
## 1 FALSE
## 2 FALSE
## 3 FALSE
## 4 FALSE
## 5 FALSE
## 6 FALSE
## EmploymentStatus.fctr.Final..rcv.glmnet.error
## 1 0.02513063
## 2 0.02760484
## 3 0.02788922
## 4 0.02804258
## 5 0.02825205
## 6 0.02830450
## .rownames EmploymentStatus.fctr
## 6758 18549 Unemployed
## 8674 61193 Disabled
## 15670 101660 Retired
## 16697 262 Not.in.Labor.Force
## 18772 488 Disabled
## 22453 77741 Disabled
## EmploymentStatus.fctr.All.X..rcv.glmnet
## 6758 Employed
## 8674 Employed
## 15670 Employed
## 16697 Employed
## 18772 <NA>
## 22453 Employed
## EmploymentStatus.fctr.All.X..rcv.glmnet.prob
## 6758 0.7504163
## 8674 0.7287896
## 15670 0.6220756
## 16697 0.6078959
## 18772 NA
## 22453 0.5189605
## EmploymentStatus.fctr.All.X..rcv.glmnet.err
## 6758 TRUE
## 8674 TRUE
## 15670 TRUE
## 16697 TRUE
## 18772 NA
## 22453 TRUE
## EmploymentStatus.fctr.All.X..rcv.glmnet.err.abs
## 6758 0.08135210
## 8674 0.02325500
## 15670 0.19227345
## 16697 0.08180032
## 18772 NA
## 22453 0.01402917
## EmploymentStatus.fctr.All.X..rcv.glmnet.is.acc
## 6758 FALSE
## 8674 FALSE
## 15670 FALSE
## 16697 FALSE
## 18772 NA
## 22453 FALSE
## EmploymentStatus.fctr.Final..rcv.glmnet
## 6758 Employed
## 8674 Employed
## 15670 Employed
## 16697 Employed
## 18772 Employed
## 22453 Employed
## EmploymentStatus.fctr.Final..rcv.glmnet.prob
## 6758 0.7536517
## 8674 0.7253134
## 15670 0.6266511
## 16697 0.6108497
## 18772 0.5766080
## 22453 0.5181191
## EmploymentStatus.fctr.Final..rcv.glmnet.err
## 6758 TRUE
## 8674 TRUE
## 15670 TRUE
## 16697 TRUE
## 18772 TRUE
## 22453 TRUE
## EmploymentStatus.fctr.Final..rcv.glmnet.err.abs
## 6758 0.07596810
## 8674 0.02438197
## 15670 0.18444870
## 16697 0.08000917
## 18772 0.10111372
## 22453 0.01415913
## EmploymentStatus.fctr.Final..rcv.glmnet.is.acc
## 6758 FALSE
## 8674 FALSE
## 15670 FALSE
## 16697 FALSE
## 18772 FALSE
## 22453 FALSE
## EmploymentStatus.fctr.Final..rcv.glmnet.accurate
## 6758 FALSE
## 8674 FALSE
## 15670 FALSE
## 16697 FALSE
## 18772 FALSE
## 22453 FALSE
## EmploymentStatus.fctr.Final..rcv.glmnet.error
## 6758 0.2463483
## 8674 0.2746866
## 15670 0.3733489
## 16697 0.3891503
## 18772 0.4233920
## 22453 0.4818809
## .rownames EmploymentStatus.fctr
## 29121 9666 Employed
## 29122 113105 Not.in.Labor.Force
## 29123 13047 Disabled
## 29124 95473 Not.in.Labor.Force
## 29125 7506 Retired
## 29126 77820 Not.in.Labor.Force
## EmploymentStatus.fctr.All.X..rcv.glmnet
## 29121 Not.in.Labor.Force
## 29122 <NA>
## 29123 Disabled
## 29124 Employed
## 29125 <NA>
## 29126 <NA>
## EmploymentStatus.fctr.All.X..rcv.glmnet.prob
## 29121 0.2824539
## 29122 NA
## 29123 0.3127349
## 29124 0.2924985
## 29125 NA
## 29126 NA
## EmploymentStatus.fctr.All.X..rcv.glmnet.err
## 29121 TRUE
## 29122 NA
## 29123 FALSE
## 29124 TRUE
## 29125 NA
## 29126 NA
## EmploymentStatus.fctr.All.X..rcv.glmnet.err.abs
## 29121 0.2745356
## 29122 NA
## 29123 0.0000000
## 29124 0.2044541
## 29125 NA
## 29126 NA
## EmploymentStatus.fctr.All.X..rcv.glmnet.is.acc
## 29121 FALSE
## 29122 NA
## 29123 TRUE
## 29124 FALSE
## 29125 NA
## 29126 NA
## EmploymentStatus.fctr.Final..rcv.glmnet
## 29121 Not.in.Labor.Force
## 29122 Employed
## 29123 Not.in.Labor.Force
## 29124 Employed
## 29125 Employed
## 29126 Employed
## EmploymentStatus.fctr.Final..rcv.glmnet.prob
## 29121 0.2942089
## 29122 0.2941387
## 29123 0.2940581
## 29124 0.2936619
## 29125 0.2749707
## 29126 0.2732929
## EmploymentStatus.fctr.Final..rcv.glmnet.err
## 29121 TRUE
## 29122 TRUE
## 29123 TRUE
## 29124 TRUE
## 29125 TRUE
## 29126 TRUE
## EmploymentStatus.fctr.Final..rcv.glmnet.err.abs
## 29121 0.2826697
## 29122 0.2918380
## 29123 0.2932583
## 29124 0.1869001
## 29125 0.2590398
## 29126 0.1962120
## EmploymentStatus.fctr.Final..rcv.glmnet.is.acc
## 29121 FALSE
## 29122 FALSE
## 29123 FALSE
## 29124 FALSE
## 29125 FALSE
## 29126 FALSE
## EmploymentStatus.fctr.Final..rcv.glmnet.accurate
## 29121 FALSE
## 29122 FALSE
## 29123 FALSE
## 29124 FALSE
## 29125 FALSE
## 29126 FALSE
## EmploymentStatus.fctr.Final..rcv.glmnet.error
## 29121 0.7057911
## 29122 0.7058613
## 29123 0.7059419
## 29124 0.7063381
## 29125 0.7250293
## 29126 0.7267071
dsp_feats_vctr <- c(NULL)
for(var in grep(".imp", names(glb_feats_df), fixed=TRUE, value=TRUE))
dsp_feats_vctr <- union(dsp_feats_vctr,
glb_feats_df[!is.na(glb_feats_df[, var]), "id"])
# print(glbObsTrn[glbObsTrn$UniqueID %in% FN_OOB_ids,
# grep(glb_rsp_var, names(glbObsTrn), value=TRUE)])
print(setdiff(names(glbObsTrn), names(glbObsAll)))## [1] "EmploymentStatus.fctr.Final..rcv.glmnet"
## [2] "EmploymentStatus.fctr.Final..rcv.glmnet.prob"
## [3] "EmploymentStatus.fctr.Final..rcv.glmnet.err"
## [4] "EmploymentStatus.fctr.Final..rcv.glmnet.err.abs"
## [5] "EmploymentStatus.fctr.Final..rcv.glmnet.is.acc"for (col in setdiff(names(glbObsTrn), names(glbObsAll)))
# Merge or cbind ?
glbObsAll[glbObsAll$.src == "Train", col] <- glbObsTrn[, col]
print(setdiff(names(glbObsFit), names(glbObsAll)))## character(0)print(setdiff(names(glbObsOOB), names(glbObsAll)))## character(0)for (col in setdiff(names(glbObsOOB), names(glbObsAll)))
# Merge or cbind ?
glbObsAll[glbObsAll$.lcn == "OOB", col] <- glbObsOOB[, col]
print(setdiff(names(glbObsNew), names(glbObsAll)))## character(0)#glb2Sav(); all.equal(savObsAll, glbObsAll); all.equal(sav_models_lst, glb_models_lst)
#load(file = paste0(glbOut$pfx, "dsk_knitr.RData"))
#cmpCols <- names(glbObsAll)[!grepl("\\.Final\\.", names(glbObsAll))]; all.equal(savObsAll[, cmpCols], glbObsAll[, cmpCols]); all.equal(savObsAll[, "H.P.http"], glbObsAll[, "H.P.http"]);
replay.petrisim(pn = glb_analytics_pn,
replay.trans = (glb_analytics_avl_objs <- c(glb_analytics_avl_objs,
"data.training.all.prediction","model.final")), flip_coord = TRUE)## time trans "bgn " "fit.data.training.all " "predict.data.new " "end "
## 0.0000 multiple enabled transitions: data.training.all data.new model.selected firing: data.training.all
## 1.0000 1 2 1 0 0
## 1.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction firing: data.new
## 2.0000 2 1 1 1 0
## 2.0000 multiple enabled transitions: data.training.all data.new model.selected model.final data.training.all.prediction data.new.prediction firing: model.selected
## 3.0000 3 0 2 1 0
## 3.0000 multiple enabled transitions: model.final data.training.all.prediction data.new.prediction firing: data.training.all.prediction
## 4.0000 5 0 1 1 1
## 4.0000 multiple enabled transitions: model.final data.training.all.prediction data.new.prediction firing: model.final
## 5.0000 4 0 0 2 1
glb_chunks_df <- myadd_chunk(glb_chunks_df, "predict.data.new", major.inc = TRUE)## label step_major step_minor label_minor bgn end
## 21 fit.data.training 9 1 1 2972.312 3052.423
## 22 predict.data.new 10 0 0 3052.423 NA
## elapsed
## 21 80.111
## 22 NAStep 10.0: predict data new
## Warning in glb_analytics_diag_plots(obs_df = glbObsNew, mdl_id =
## glb_fin_mdl_id, : Limiting important feature scatter plots to 5 out of 10## Warning: Removed 25789 rows containing missing values (geom_point).
## Warning: Removed 25789 rows containing missing values (geom_point).
## Warning: Removed 25789 rows containing missing values (geom_point).
## Warning: Removed 25789 rows containing missing values (geom_point).
## Warning: Removed 25789 rows containing missing values (geom_point).
## Warning: Removed 25789 rows containing missing values (geom_point).
## Warning: Removed 25789 rows containing missing values (geom_point).
## Warning: Removed 25789 rows containing missing values (geom_point).
## Warning: Removed 25789 rows containing missing values (geom_point).
## Warning: Removed 25789 rows containing missing values (geom_point).
## NULL## Loading required package: tidyr##
## Attaching package: 'tidyr'## The following object is masked from 'package:Matrix':
##
## expand## [1] "OOBobs total range outliers: 0"
## [1] "newobs EmploymentStatus.fctr.Final..rcv.glmnet Employed: min < min of Train range: 24451"
## .rownames EmploymentStatus.fctr.Final..rcv.glmnet Age
## 2 91211 Employed 11
## 16 92332 Employed 8
## 27 92480 Employed 6
## 33 92056 Employed 0
## 42 91863 Employed 7
## 47 93035 Employed 1
## .rownames EmploymentStatus.fctr.Final..rcv.glmnet Age
## 11326 39860 Employed 2
## 22350 81743 Employed 10
## 39062 12105 Employed 12
## 50138 83384 Employed 14
## 55093 56439 Employed 8
## 97641 70549 Employed 0
## .rownames EmploymentStatus.fctr.Final..rcv.glmnet Age
## 131249 27532 Employed 4
## 131253 53684 Employed 5
## 131261 32548 Employed 2
## 131266 109385 Employed 13
## 131286 53685 Employed 6
## 131288 81739 Employed 14
## id cor.y exclude.as.feat cor.y.abs cor.high.X freqRatio
## Age Age 0.279553 FALSE 0.279553 NA 1.089125
## percentUnique zeroVar nzv is.cor.y.abs.low interaction.feat
## Age 0.06349928 FALSE FALSE FALSE NA
## shapiro.test.p.value rsp_var_raw rsp_var max min
## Age 1.847733e-31 FALSE NA 85 0
## max.EmploymentStatus.fctr.Disabled max.EmploymentStatus.fctr.Employed
## Age 85 85
## max.EmploymentStatus.fctr.Not.in.Labor.Force
## Age 85
## max.EmploymentStatus.fctr.Retired max.EmploymentStatus.fctr.Unemployed
## Age 85 85
## min.EmploymentStatus.fctr.Disabled min.EmploymentStatus.fctr.Employed
## Age 15 15
## min.EmploymentStatus.fctr.Not.in.Labor.Force
## Age 15
## min.EmploymentStatus.fctr.Retired min.EmploymentStatus.fctr.Unemployed
## Age 16 15
## max.EmploymentStatus.fctr.All.X..rcv.glmnet.Disabled
## Age 71
## max.EmploymentStatus.fctr.All.X..rcv.glmnet.Employed
## Age 74
## max.EmploymentStatus.fctr.All.X..rcv.glmnet.Not.in.Labor.Force
## Age 61
## max.EmploymentStatus.fctr.All.X..rcv.glmnet.Retired
## Age 85
## min.EmploymentStatus.fctr.All.X..rcv.glmnet.Disabled
## Age 43
## min.EmploymentStatus.fctr.All.X..rcv.glmnet.Employed
## Age 15
## min.EmploymentStatus.fctr.All.X..rcv.glmnet.Not.in.Labor.Force
## Age 15
## min.EmploymentStatus.fctr.All.X..rcv.glmnet.Retired
## Age 60
## max.EmploymentStatus.fctr.Final..rcv.glmnet.Employed
## Age 61
## max.EmploymentStatus.fctr.Final..rcv.glmnet.Not.in.Labor.Force
## Age 21
## min.EmploymentStatus.fctr.Final..rcv.glmnet.Employed
## Age 0
## min.EmploymentStatus.fctr.Final..rcv.glmnet.Not.in.Labor.Force
## Age 0
## [1] "newobs EmploymentStatus.fctr.Final..rcv.glmnet Not.in.Labor.Force: min < min of Train range: 887"
## .rownames EmploymentStatus.fctr.Final..rcv.glmnet Age
## 100 34795 Not.in.Labor.Force 7
## 102 34793 Not.in.Labor.Force 6
## 145 35046 Not.in.Labor.Force 5
## 197 34794 Not.in.Labor.Force 6
## 254 84130 Not.in.Labor.Force 3
## 457 80243 Not.in.Labor.Force 5
## .rownames EmploymentStatus.fctr.Final..rcv.glmnet Age
## 14587 91687 Not.in.Labor.Force 2
## 24610 80751 Not.in.Labor.Force 2
## 27281 101185 Not.in.Labor.Force 4
## 52743 82549 Not.in.Labor.Force 6
## 73751 6656 Not.in.Labor.Force 12
## 87070 115279 Not.in.Labor.Force 9
## .rownames EmploymentStatus.fctr.Final..rcv.glmnet Age
## 131022 51446 Not.in.Labor.Force 7
## 131067 81761 Not.in.Labor.Force 9
## 131078 81760 Not.in.Labor.Force 6
## 131093 81762 Not.in.Labor.Force 12
## 131148 118082 Not.in.Labor.Force 1
## 131298 37126 Not.in.Labor.Force 4
## id cor.y exclude.as.feat cor.y.abs cor.high.X freqRatio
## Age Age 0.279553 FALSE 0.279553 NA 1.089125
## percentUnique zeroVar nzv is.cor.y.abs.low interaction.feat
## Age 0.06349928 FALSE FALSE FALSE NA
## shapiro.test.p.value rsp_var_raw rsp_var max min
## Age 1.847733e-31 FALSE NA 85 0
## max.EmploymentStatus.fctr.Disabled max.EmploymentStatus.fctr.Employed
## Age 85 85
## max.EmploymentStatus.fctr.Not.in.Labor.Force
## Age 85
## max.EmploymentStatus.fctr.Retired max.EmploymentStatus.fctr.Unemployed
## Age 85 85
## min.EmploymentStatus.fctr.Disabled min.EmploymentStatus.fctr.Employed
## Age 15 15
## min.EmploymentStatus.fctr.Not.in.Labor.Force
## Age 15
## min.EmploymentStatus.fctr.Retired min.EmploymentStatus.fctr.Unemployed
## Age 16 15
## max.EmploymentStatus.fctr.All.X..rcv.glmnet.Disabled
## Age 71
## max.EmploymentStatus.fctr.All.X..rcv.glmnet.Employed
## Age 74
## max.EmploymentStatus.fctr.All.X..rcv.glmnet.Not.in.Labor.Force
## Age 61
## max.EmploymentStatus.fctr.All.X..rcv.glmnet.Retired
## Age 85
## min.EmploymentStatus.fctr.All.X..rcv.glmnet.Disabled
## Age 43
## min.EmploymentStatus.fctr.All.X..rcv.glmnet.Employed
## Age 15
## min.EmploymentStatus.fctr.All.X..rcv.glmnet.Not.in.Labor.Force
## Age 15
## min.EmploymentStatus.fctr.All.X..rcv.glmnet.Retired
## Age 60
## max.EmploymentStatus.fctr.Final..rcv.glmnet.Employed
## Age 61
## max.EmploymentStatus.fctr.Final..rcv.glmnet.Not.in.Labor.Force
## Age 21
## min.EmploymentStatus.fctr.Final..rcv.glmnet.Employed
## Age 0
## min.EmploymentStatus.fctr.Final..rcv.glmnet.Not.in.Labor.Force
## Age 0
## [1] "newobs total range outliers: 25338"## [1] TRUE## [1] "glb_sel_mdl_id: All.X##rcv#glmnet"## [1] "glb_fin_mdl_id: Final##rcv#glmnet"## [1] "Cross Validation issues:"
## MFO###myMFO_classfr Random###myrandom_classfr
## 0 0
## Max.cor.Y.rcv.1X1###glmnet
## 0## max.Accuracy.OOB max.Kappa.OOB
## Max.cor.Y##rcv#rpart 0.7276701 0.4783438508
## All.X##rcv#glmnet 0.7229115 0.4729121383
## Max.cor.Y.rcv.1X1###glmnet 0.6859711 0.3481272164
## MFO###myMFO_classfr 0.5850546 0.0000000000
## Random###myrandom_classfr 0.3991540 0.0006568311
## Final##rcv#glmnet NA NA## [1] "All.X##rcv#glmnet OOB confusion matrix & accuracy: "
## Prediction
## Reference Disabled Employed Not.in.Labor.Force Retired
## Disabled 82 1169 70 215
## Employed 50 15141 614 793
## Not.in.Labor.Force 17 2429 1545 108
## Retired 26 1234 5 3741
## Unemployed 6 948 150 27
## Prediction
## Reference Unemployed
## Disabled 0
## Employed 0
## Not.in.Labor.Force 0
## Retired 0
## Unemployed 0## err.abs.fit.sum err.abs.OOB.sum err.abs.trn.sum err.abs.new.sum
## .dummy 3967.069 1481.543 5451.929 NA
## .freqRatio.Fit .freqRatio.OOB .freqRatio.Tst .n.Fit .n.New.Employed
## .dummy 1 1 1 77143 24900
## .n.New.Not.in.Labor.Force .n.OOB .n.Trn.Disabled .n.Trn.Employed
## .dummy 889 28370 5712 61733
## .n.Trn.Not.in.Labor.Force .n.Trn.Retired .n.Trn.Unemployed .n.Tst
## .dummy 15246 18619 4203 25789
## .n.fit .n.new .n.trn err.abs.OOB.mean err.abs.fit.mean
## .dummy 77143 25789 105513 0.05222217 0.05142488
## err.abs.new.mean err.abs.trn.mean
## .dummy NA 0.05167068
## err.abs.fit.sum err.abs.OOB.sum
## 3.967069e+03 1.481543e+03
## err.abs.trn.sum err.abs.new.sum
## 5.451929e+03 NA
## .freqRatio.Fit .freqRatio.OOB
## 1.000000e+00 1.000000e+00
## .freqRatio.Tst .n.Fit
## 1.000000e+00 7.714300e+04
## .n.New.Employed .n.New.Not.in.Labor.Force
## 2.490000e+04 8.890000e+02
## .n.OOB .n.Trn.Disabled
## 2.837000e+04 5.712000e+03
## .n.Trn.Employed .n.Trn.Not.in.Labor.Force
## 6.173300e+04 1.524600e+04
## .n.Trn.Retired .n.Trn.Unemployed
## 1.861900e+04 4.203000e+03
## .n.Tst .n.fit
## 2.578900e+04 7.714300e+04
## .n.new .n.trn
## 2.578900e+04 1.055130e+05
## err.abs.OOB.mean err.abs.fit.mean
## 5.222217e-02 5.142488e-02
## err.abs.new.mean err.abs.trn.mean
## NA 5.167068e-02## [1] "Features Importance for selected models:"## All.X..rcv.glmnet.imp.Disabled
## Education.fctrNo high school diploma 100.0000000
## Married.fctrMarried 80.5845919
## Education.fctrMaster's degree 81.6105115
## Citizenship.fctrNon-Citizen 80.8187616
## Education.fctrDoctorate degree 58.8506019
## Education.fctrProfessional degree 71.1360427
## Married.fctrWidowed 0.0000000
## Sex.fctrMale 0.0000000
## Race.fctrBlack 29.1551897
## Education.fctrHigh school 34.0699104
## Education.fctrBachelor's degree 59.1559838
## Citizenship.fctrCitizen, Naturalized 47.4802548
## Race.fctrAmerican Indian 0.8471631
## Race.fctrAsian 6.8442014
## Married.fctrNever Married 0.0000000
## Education.fctrSome college, no degree 10.8622226
## All.X..rcv.glmnet.imp.Employed
## Education.fctrNo high school diploma 80.094677
## Married.fctrMarried 0.000000
## Education.fctrMaster's degree 24.226282
## Citizenship.fctrNon-Citizen 7.227984
## Education.fctrDoctorate degree 72.186222
## Education.fctrProfessional degree 50.306390
## Married.fctrWidowed 11.058165
## Sex.fctrMale 20.843611
## Race.fctrBlack 19.032460
## Education.fctrHigh school 42.836408
## Education.fctrBachelor's degree 14.350902
## Citizenship.fctrCitizen, Naturalized 7.787895
## Race.fctrAmerican Indian 34.669462
## Race.fctrAsian 0.000000
## Married.fctrNever Married 19.383808
## Education.fctrSome college, no degree 20.401790
## All.X..rcv.glmnet.imp.Not.in.Labor.Force
## Education.fctrNo high school diploma 90.911477
## Married.fctrMarried 24.377008
## Education.fctrMaster's degree 3.826702
## Citizenship.fctrNon-Citizen 14.922307
## Education.fctrDoctorate degree 0.000000
## Education.fctrProfessional degree 0.000000
## Married.fctrWidowed 54.767522
## Sex.fctrMale 67.291846
## Race.fctrBlack 8.553671
## Education.fctrHigh school 0.000000
## Education.fctrBachelor's degree 0.000000
## Citizenship.fctrCitizen, Naturalized 3.886102
## Race.fctrAmerican Indian 0.000000
## Race.fctrAsian 41.270984
## Married.fctrNever Married 31.347716
## Education.fctrSome college, no degree 21.607572
## All.X..rcv.glmnet.imp.Retired
## Education.fctrNo high school diploma 0.000000
## Married.fctrMarried 38.363589
## Education.fctrMaster's degree 22.158309
## Citizenship.fctrNon-Citizen 27.377846
## Education.fctrDoctorate degree 3.271762
## Education.fctrProfessional degree 0.000000
## Married.fctrWidowed 49.553115
## Sex.fctrMale 10.528453
## Race.fctrBlack 0.000000
## Education.fctrHigh school 7.143373
## Education.fctrBachelor's degree 3.867177
## Citizenship.fctrCitizen, Naturalized 19.780937
## Race.fctrAmerican Indian 16.946844
## Race.fctrAsian 14.009402
## Married.fctrNever Married 4.632821
## Education.fctrSome college, no degree 0.000000
## All.X..rcv.glmnet.imp.Unemployed
## Education.fctrNo high school diploma 11.0521930
## Married.fctrMarried 50.7011130
## Education.fctrMaster's degree 0.0000000
## Citizenship.fctrNon-Citizen 0.0000000
## Education.fctrDoctorate degree 0.0000000
## Education.fctrProfessional degree 0.0000000
## Married.fctrWidowed 10.6888708
## Sex.fctrMale 21.5884246
## Race.fctrBlack 46.9542665
## Education.fctrHigh school 0.5911445
## Education.fctrBachelor's degree 0.0000000
## Citizenship.fctrCitizen, Naturalized 0.0000000
## Race.fctrAmerican Indian 21.2926566
## Race.fctrAsian 5.1886845
## Married.fctrNever Married 2.4655739
## Education.fctrSome college, no degree 0.3188346
## Final..rcv.glmnet.imp.Disabled
## Education.fctrNo high school diploma 100.000000
## Married.fctrMarried 81.246159
## Education.fctrMaster's degree 79.951444
## Citizenship.fctrNon-Citizen 80.712770
## Education.fctrDoctorate degree 55.015897
## Education.fctrProfessional degree 78.558535
## Married.fctrWidowed 0.000000
## Sex.fctrMale 0.000000
## Race.fctrBlack 32.851713
## Education.fctrHigh school 33.098847
## Education.fctrBachelor's degree 63.921032
## Citizenship.fctrCitizen, Naturalized 46.351000
## Race.fctrAmerican Indian 5.675508
## Race.fctrAsian 5.460627
## Married.fctrNever Married 0.000000
## Education.fctrSome college, no degree 4.114656
## Final..rcv.glmnet.imp.Employed
## Education.fctrNo high school diploma 77.628938
## Married.fctrMarried 0.000000
## Education.fctrMaster's degree 28.313848
## Citizenship.fctrNon-Citizen 10.051168
## Education.fctrDoctorate degree 69.723991
## Education.fctrProfessional degree 55.506180
## Married.fctrWidowed 4.423530
## Sex.fctrMale 20.302323
## Race.fctrBlack 15.477478
## Education.fctrHigh school 40.875713
## Education.fctrBachelor's degree 14.181781
## Citizenship.fctrCitizen, Naturalized 6.892279
## Race.fctrAmerican Indian 28.796180
## Race.fctrAsian 0.000000
## Married.fctrNever Married 18.771361
## Education.fctrSome college, no degree 19.314050
## Final..rcv.glmnet.imp.Not.in.Labor.Force
## Education.fctrNo high school diploma 92.4379866
## Married.fctrMarried 22.9633810
## Education.fctrMaster's degree 3.4239386
## Citizenship.fctrNon-Citizen 15.9235833
## Education.fctrDoctorate degree 0.0000000
## Education.fctrProfessional degree 0.0000000
## Married.fctrWidowed 63.0646928
## Sex.fctrMale 69.2621101
## Race.fctrBlack 4.3252103
## Education.fctrHigh school 0.6234842
## Education.fctrBachelor's degree 0.0000000
## Citizenship.fctrCitizen, Naturalized 0.0000000
## Race.fctrAmerican Indian 0.0000000
## Race.fctrAsian 41.7507091
## Married.fctrNever Married 30.7054464
## Education.fctrSome college, no degree 24.0160296
## Final..rcv.glmnet.imp.Retired
## Education.fctrNo high school diploma 0.000000
## Married.fctrMarried 34.830347
## Education.fctrMaster's degree 24.998385
## Citizenship.fctrNon-Citizen 27.065976
## Education.fctrDoctorate degree 0.000000
## Education.fctrProfessional degree 0.000000
## Married.fctrWidowed 51.037204
## Sex.fctrMale 9.656200
## Race.fctrBlack 0.000000
## Education.fctrHigh school 6.241790
## Education.fctrBachelor's degree 7.772573
## Citizenship.fctrCitizen, Naturalized 20.694932
## Race.fctrAmerican Indian 2.938171
## Race.fctrAsian 12.944049
## Married.fctrNever Married 6.981007
## Education.fctrSome college, no degree 0.000000
## Final..rcv.glmnet.imp.Unemployed
## Education.fctrNo high school diploma 8.457547
## Married.fctrMarried 53.574303
## Education.fctrMaster's degree 0.000000
## Citizenship.fctrNon-Citizen 0.000000
## Education.fctrDoctorate degree 0.000000
## Education.fctrProfessional degree 0.000000
## Married.fctrWidowed 5.258252
## Sex.fctrMale 15.977102
## Race.fctrBlack 49.959778
## Education.fctrHigh school 0.000000
## Education.fctrBachelor's degree 0.000000
## Citizenship.fctrCitizen, Naturalized 0.000000
## Race.fctrAmerican Indian 35.242184
## Race.fctrAsian 0.000000
## Married.fctrNever Married 0.501794
## Education.fctrSome college, no degree 0.000000
## imp.mean
## Education.fctrNo high school diploma 56.05828
## Married.fctrMarried 38.66405
## Education.fctrMaster's degree 26.85094
## Citizenship.fctrNon-Citizen 26.41004
## Education.fctrDoctorate degree 25.90485
## Education.fctrProfessional degree 25.55071
## Married.fctrWidowed 24.98514
## Sex.fctrMale 23.54501
## Race.fctrBlack 20.63098
## Education.fctrHigh school 16.54807
## Education.fctrBachelor's degree 16.32494
## Citizenship.fctrCitizen, Naturalized 15.28734
## Race.fctrAmerican Indian 14.64082
## Race.fctrAsian 12.74687
## Married.fctrNever Married 11.47895
## Education.fctrSome college, no degree 10.06352## [1] "glbObsNew prediction stats:"##
## Disabled Employed Not.in.Labor.Force
## 0 24900 889
## Retired Unemployed
## 0 0## label step_major step_minor label_minor bgn
## 22 predict.data.new 10 0 0 3052.423
## 23 display.session.info 11 0 0 3134.169
## end elapsed
## 22 3134.168 81.746
## 23 NA NANull Hypothesis (\(\sf{H_{0}}\)): mpg is not impacted by am_fctr.
The variance by am_fctr appears to be independent. #{r q1, cache=FALSE} # print(t.test(subset(cars_df, am_fctr == "automatic")$mpg, # subset(cars_df, am_fctr == "manual")$mpg, # var.equal=FALSE)$conf) # We reject the null hypothesis i.e. we have evidence to conclude that am_fctr impacts mpg (95% confidence). Manual transmission is better for miles per gallon versus automatic transmission.
## label step_major step_minor label_minor bgn
## 20 fit.data.training 9 0 0 1331.743
## 17 fit.models 8 1 1 153.030
## 22 predict.data.new 10 0 0 3052.423
## 21 fit.data.training 9 1 1 2972.312
## 2 inspect.data 2 0 0 30.031
## 16 fit.models 8 0 0 118.503
## 18 fit.models 8 2 2 1278.196
## 19 fit.models 8 3 3 1310.740
## 1 import.data 1 0 0 9.784
## 4 transform.data 2 2 2 78.514
## 15 select.features 7 0 0 107.383
## 14 partition.data.training 6 0 0 101.177
## 5 extract.features 3 0 0 92.220
## 3 scrub.data 2 1 1 73.211
## 12 manage.missing.data 4 0 0 99.484
## 11 extract.features.end 3 6 6 98.568
## 13 cluster.data 5 0 0 100.642
## 10 extract.features.string 3 5 5 98.220
## 7 extract.features.image 3 2 2 98.062
## 9 extract.features.text 3 4 4 98.168
## 8 extract.features.price 3 3 3 98.129
## 6 extract.features.datetime 3 1 1 98.024
## end elapsed duration
## 20 2972.311 1640.568 1640.568
## 17 1278.195 1125.166 1125.165
## 22 3134.168 81.746 81.745
## 21 3052.423 80.111 80.111
## 2 73.211 43.180 43.180
## 16 153.030 34.527 34.527
## 18 1310.739 32.544 32.543
## 19 1331.742 21.002 21.002
## 1 30.030 20.246 20.246
## 4 92.220 13.706 13.706
## 15 118.503 11.120 11.120
## 14 107.382 6.206 6.205
## 5 98.023 5.804 5.803
## 3 78.514 5.303 5.303
## 12 100.641 1.157 1.157
## 11 99.484 0.916 0.916
## 13 101.177 0.535 0.535
## 10 98.567 0.347 0.347
## 7 98.129 0.067 0.067
## 9 98.219 0.052 0.051
## 8 98.167 0.038 0.038
## 6 98.061 0.038 0.037
## [1] "Total Elapsed Time: 3,134.168 secs"